# AI Video Atlas

> Give your AI agent a video director. AI Video Atlas is a free, read-only MCP server and REST API for AI video: shot plans, model picks for a budget, vendor-stated prices per second, sourced prompts, prompting guides and workflows. No account or API key. This website is the browsable view of the same data. Every item credits its creator and links its primary source.

## Agents
- MCP server (streamable HTTP, no auth): https://mcp.aivideoatlas.com/mcp
- Tools: plan_shots, find_shot, best_prompt, recommend_model, get_prices, get_workflow, get_guide, whats_new
- REST API + OpenAPI: https://mcp.aivideoatlas.com/openapi.json
- Agent guide: https://mcp.aivideoatlas.com/guide.md
- Examples: https://mcp.aivideoatlas.com/examples.md
- How to connect: https://aivideoatlas.com/agents/

## Core
- [Shots](https://aivideoatlas.com/): browsable view of the shot library
- [Prices](https://aivideoatlas.com/prices/): vendor-stated $/second with sources and check dates
- [Cheapest AI video generators](https://aivideoatlas.com/cheapest-ai-video-generator/)
- [Guides](https://aivideoatlas.com/guides/): workflows and tools by job
- [All listings](https://aivideoatlas.com/all/)

## Prompt hubs
- [Seedance prompts](https://aivideoatlas.com/prompts/seedance/)
- [Kling prompts](https://aivideoatlas.com/prompts/kling/)
- [Veo prompts](https://aivideoatlas.com/prompts/veo/)

## Shot types
- [Ads that sell](https://aivideoatlas.com/shot-types/ads/): 21 shots
- [Music videos](https://aivideoatlas.com/shot-types/music/): 2 shots
- [Viral shorts](https://aivideoatlas.com/shot-types/shorts/): 23 shots
- [Consistent characters](https://aivideoatlas.com/shot-types/characters/): 26 shots
- [Product shots](https://aivideoatlas.com/shot-types/product/): 12 shots
- [Cinematic / drone](https://aivideoatlas.com/shot-types/cinematic/): 67 shots
- [Lip sync & dialogue](https://aivideoatlas.com/shot-types/lipsync/): 13 shots
- [Animation / anime](https://aivideoatlas.com/shot-types/anime/): 17 shots

## Models
- [Seedance](https://aivideoatlas.com/models/seedance/): 40 shots, from $0.16/s
- [Kling](https://aivideoatlas.com/models/kling/): 24 shots, from $0.07/s
- [Veo](https://aivideoatlas.com/models/veo/): 20 shots, from $0.05/s
- [Luma](https://aivideoatlas.com/models/luma/): 17 shots, from $0.03/s
- [Runway](https://aivideoatlas.com/models/runway/): 13 shots, from $0.05/s
- [Hailuo](https://aivideoatlas.com/models/hailuo/): 12 shots, from $0.1/s
- [Sora](https://aivideoatlas.com/models/sora/): 6 shots
- [LTX](https://aivideoatlas.com/models/ltx/): 3 shots, from $0.06/s
- [Higgsfield](https://aivideoatlas.com/models/higgsfield/): 1 shots, from $0.0578/s
- [Wan](https://aivideoatlas.com/models/wan/): 1 shots, from $0.05/s
- [Grok Imagine](https://aivideoatlas.com/models/grok/): 0 shots, from $0.02/s
- [Vivix](https://aivideoatlas.com/models/vivix/): 0 shots, from $0.003/s

## Comparisons
- [Kling vs Seedance](https://aivideoatlas.com/models/kling/vs-seedance/)
- [Veo vs Kling](https://aivideoatlas.com/models/veo/vs-kling/)
- [Seedance vs Veo](https://aivideoatlas.com/models/seedance/vs-veo/)
- [Hailuo vs Kling](https://aivideoatlas.com/models/hailuo/vs-kling/)
- [Wan vs LTX](https://aivideoatlas.com/models/wan/vs-ltx/)
- [Runway vs Luma](https://aivideoatlas.com/models/runway/vs-luma/)
- [Veo vs Runway](https://aivideoatlas.com/models/veo/vs-runway/)
- [Seedance vs Wan](https://aivideoatlas.com/models/seedance/vs-wan/)
- [Hailuo vs Seedance](https://aivideoatlas.com/models/hailuo/vs-seedance/)
- [Hailuo vs Veo](https://aivideoatlas.com/models/hailuo/vs-veo/)
- [Runway vs Kling](https://aivideoatlas.com/models/runway/vs-kling/)
- [Luma vs Kling](https://aivideoatlas.com/models/luma/vs-kling/)
- [Luma vs Veo](https://aivideoatlas.com/models/luma/vs-veo/)
- [Kling vs Grok Imagine](https://aivideoatlas.com/models/kling/vs-grok/)
- [Seedance vs Grok Imagine](https://aivideoatlas.com/models/seedance/vs-grok/)
- [Veo vs Grok Imagine](https://aivideoatlas.com/models/veo/vs-grok/)
- [Higgsfield vs Kling](https://aivideoatlas.com/models/higgsfield/vs-kling/)

## Shots
- [A one-vs-crew alley fight scene from a single Kling 3.0 prompt](https://aivideoatlas.com/shots/alley-fight-action-thriller-kling-3-0-taliaaariz/): Wrote one long prompt for a night-alley standoff in which a lone woman faces a crew, spelling out blocking, lighting and camera notes shot by shot.
- [A street vlog that looks like it was shot on a 2011 phone](https://aivideoatlas.com/shots/2011-smartphone-street-vlog-look-seedance-2-5-just-sharon7/): Asked for early-2010s phone flaws on purpose: selfie framing, 480p noise, compression blocks, rolling shutter and white-balance shifts.
- [Sunrise breakfast vlog in home-video style (Seedance 2.5)](https://aivideoatlas.com/shots/sunrise-breakfast-vlog-in-home-video-style-seedance-2-5-just-sharon7/): A detailed prompt for a raw, handheld early-2000s home-video look in a sunny kitchen, with strict rules to keep the reference character's face and outfit…
- [Multishot fashion UGC party vlog (Kling 4.0 Flash)](https://aivideoatlas.com/shots/multishot-fashion-ugc-party-vlog-kling-4-0-flash-diplomeme/): A structured 20-second vertical prompt for a creator vlogging a party outfit across several shots. It shows how to lay out a multishot UGC brief.
- [Early-2000s Korean MiniDV home video look (Seedance 2.5)](https://aivideoatlas.com/shots/early-2000s-korean-minidv-home-video-look-seedance-2-5-mehvishs25/): A detailed prompt for an original character filmed like 2002–2005 MiniDV home footage. It's useful for nailing a period camcorder look.
- [A 20-second fight that keeps the same character through every strike](https://aivideoatlas.com/shots/timed-multi-move-fight-scene-with-a-locked-character-kling-4-itxabdullaa/): Wrote a second-by-second prompt that pins an original character to a reference image and chains strikes without resets.
- [Slow-motion lipstick beauty commercial (Seedance 2.5)](https://aivideoatlas.com/shots/slow-motion-lipstick-beauty-commercial-seedance-2-5-meenakshiyacs/): A two-reference product prompt (one image for the lipstick, one for the model and car) for a slow-motion beauty ad with precise product tracking.
- [Feeding stray cats, camcorder vlog (Seedance 2.5)](https://aivideoatlas.com/shots/feeding-stray-cats-camcorder-vlog-seedance-2-5-strength04-x/): A prompt for a gentle, ASMR-style outdoor vlog shot like handheld mini-DV footage, with the sounds to emphasise listed out.
- [Miniature aerospace diorama commercial, JSON prompt (Veo 3.1)](https://aivideoatlas.com/shots/miniature-aerospace-diorama-commercial-json-prompt-veo-3-1-fujimoto-hina/): A JSON-structured Veo 3.1 prompt for a 10-second hyper-real miniature aerospace diorama ad. The fields split title, duration, format, style and prompt.
- [Fake 1985 Times Square tourist footage on VHS](https://aivideoatlas.com/shots/times-square-1985-vhs-tourist-footage-seedance-2-5-aiwithsynthia/): Wrote a historical-recreation prompt asking Seedance 2.5 for gritty 1985 Times Square, shot like a consumer camcorder.
- [MiniDV home video, same character (Seedance 2.5)](https://aivideoatlas.com/shots/minidv-home-video-same-character-seedance-2-5-iamahmedfaraz6/): A 15-second early-2000s MiniDV prompt that repeats exact character details to keep her consistent across shots.
- [A 10-second miniature-diorama gelato ad from a reusable JSON prompt](https://aivideoatlas.com/shots/miniature-banana-gelato-food-ad-json-prompt-veo-3-1-fujimoto-hina/): Wrote a JSON-format Veo 3.1 prompt for an artisanal gelato ad in a miniature style, structured so you can swap the product.
- [A UGC walk-and-talk ad for a camera brand that doesn't exist](https://aivideoatlas.com/shots/ugc-camera-product-walk-and-talk-seedance-2-5-aiwithkhan/): Used a short Seedance 2.5 prompt on OpenArt to have a creator show off a fictional camera while exploring a city.
- [A one-take UGC short: cutting a cat cake in front of the real cat](https://aivideoatlas.com/shots/one-take-kitchen-ugc-cat-cake-vs-real-cat-seedance-2-5-naiknelofar788/): Prompted Seedance 2.5 for a front-camera single take where slicing a cat-shaped cake gets a reaction from a real cat.
- [Miniature lychee sorbet food ad, JSON prompt (Veo 3.1)](https://aivideoatlas.com/shots/miniature-lychee-sorbet-food-ad-json-prompt-veo-3-1-fujimoto-hina/): A JSON-structured Veo 3.1 food-commercial prompt that builds a hyper-real miniature diorama around a sorbet.
- [A 12-second vertical sequence that follows a storyboard exactly](https://aivideoatlas.com/shots/storyboard-guided-vertical-sequence-seedance-2-5-elsasofia-ai/): Gave Seedance 2.5 a character reference plus one master storyboard image and told it to treat both as strict guides.
- [Wordless post-apocalyptic love story (Seedance 2.5)](https://aivideoatlas.com/shots/wordless-post-apocalyptic-love-story-seedance-2-5-sheldon056/): A 24-second, 24fps prompt that tells a love story between two survivors purely through visuals, with no dialogue.
- [Dojo martial arts training scene (Seedance 2.0)](https://aivideoatlas.com/shots/dojo-martial-arts-training-scene-seedance-2-0-aiwithminal/): A realistic training-scene prompt with two martial artists sparring in a wooden Japanese dojo, with notes on lighting and movement.
- [A believable handheld NYC vlog with a consistent outfit](https://aivideoatlas.com/shots/handheld-nyc-city-walk-vlog-caliraval/): Wrote a shaky follow-cam prompt of a woman walking through New York and locked her look with exact wardrobe details.
- [Miniature luxury tech diorama, JSON prompt (Veo 3.1)](https://aivideoatlas.com/shots/miniature-luxury-tech-diorama-json-prompt-veo-3-1-fujimoto-hina/): Another JSON-format Veo 3.1 prompt from the same creator, this time a desert-themed miniature tech product ad.
- [School hallway K-drama comedy beat (Seedance 2.5)](https://aivideoatlas.com/shots/school-hallway-k-drama-comedy-beat-seedance-2-5-aiwithsaira/): A 30-second comedy prompt set in a school hallway that uses an attached image to lock both characters' looks.
- [A photoreal travel vlog where a sunset walk turns into an adventure](https://aivideoatlas.com/shots/golden-hour-travel-vlog-detour-seedance-2-5-aiwithaly/): Prompted Seedance 2.5 for an ordinary golden-hour walk that detours onto a hidden trail, shot vlog-style.
- [A 25-second pop music video from one structured prompt](https://aivideoatlas.com/shots/rainy-neon-pop-music-video-seedance-2-0-caliraval/): Split the prompt into style, story and shot sections around rainy neon streets so Seedance 2.0 could cut a full music-video sequence.
- [Professional vertical product commercial (Seedance 2.5)](https://aivideoatlas.com/shots/professional-vertical-product-commercial-seedance-2-5-noorwithwifi/): A long, shot-specified commercial prompt written to look like real professional camera footage.
- [Sunny London street anime clip (Seedance 2.5)](https://aivideoatlas.com/shots/sunny-london-street-anime-clip-seedance-2-5-techiebysa/): A 20-second anime prompt with labelled character blocks (look, outfit, behaviour) on a bright London street.
- [Gothic ink anime sword fight (Seedance 2.5)](https://aivideoatlas.com/shots/gothic-ink-anime-sword-fight-seedance-2-5-aimikoda/): A style-heavy prompt that fuses 2D dark-fantasy anime with gothic ink illustration for high-sakuga sword choreography, preserving a reference aesthetic.
- [A full UGC drink ad from one prompt through Kling's MCP](https://aivideoatlas.com/shots/ugc-talking-head-beverage-ad-via-kling-mcp-aiwithkhan/): Asked Kling, via its MCP server, for an influencer-style talking head introducing a mango passionfruit drink.
- [Payday mini-vlog with timed scenes (Seedance 2.5)](https://aivideoatlas.com/shots/payday-mini-vlog-with-timed-scenes-seedance-2-5-noor-ul-ain43/): A UGC mini-vlog prompt broken into timed scenes (0–5s and so on) across one character's day. It's a useful template for scene timing.
- [Neon-city music video with three singers (Seedance 2.5)](https://aivideoatlas.com/shots/neon-city-music-video-with-three-singers-seedance-2-5-chillaikalan/): A long music-video prompt with three singers performing at night in a neon city, with lip-sync and high-budget MV direction.
- [A luxury perfume product shot with golden smoke](https://aivideoatlas.com/shots/luxury-perfume-bottle-product-shot-seedance-2-0-caliraval/): Used a compact Seedance 2.0 prompt: bottle on glossy black, amber light, golden smoke.
- [Creature breaks out of a cinema screen, one take (Seedance 2.5)](https://aivideoatlas.com/shots/creature-breaks-out-of-a-cinema-screen-one-take-seedance-2-5-shushant-l/): A strict single-take prompt that forbids any cut: a creature appears to break out of a theatre screen, filmed on a phone.
- [Pack goat rescue, one handheld take (Seedance 2.5)](https://aivideoatlas.com/shots/pack-goat-rescue-one-handheld-take-seedance-2-5-measifai/): A 20-second vertical, single-take, phone-camera prompt that tells a small rescue story (a goat leads a hiker to a trapped man) in documentary style.
- [A neon-rain cyberpunk android scene with glitching holograms](https://aivideoatlas.com/shots/cyberpunk-android-at-a-vending-machine-luma-ray-3-ludoviccreator/): Prompted Luma Ray 3 for an android at a vending machine in the rain, with holographic glitches, a metal faceplate and a pulsing skyline.
- [A survival-film blizzard shot: aerial pull-in on a collapsing climber](https://aivideoatlas.com/shots/mountaineer-in-a-blizzard-slow-push-in-luma-ray-3-ludoviccreator/): Prompted Luma Ray 3 for a wide aerial that pushes in on a climber going down on a ridge, with snow whipping across the lens.
- [A war-film crane shot: soldiers march out of smoke as a building falls](https://aivideoatlas.com/shots/crane-descent-soldiers-emerge-from-smoke-hailuo-2-3-ludoviccreator/): Prompted Hailuo 2.3 for a slow-motion crane down onto soldiers emerging from smoke with a collapse behind them.
- [A title card that forms out of volcanic ash](https://aivideoatlas.com/shots/text-vfx-word-forms-in-volcanic-ash-runway-gen-4-5-charaspowerai/): Prompted Runway Gen-4.5 to dive through swirling ash and embers that spell "WRATH" before the eruption swallows it. Swap in your own word.
- [A post-apocalyptic desert ride at golden hour, shot like live action](https://aivideoatlas.com/shots/desert-highway-motorcyclist-at-golden-hour-luma-ray-3-ludoviccreator/): Prompted Luma Ray 3 for a wide shot of a motorcyclist with dust trails, long shadows and wrecked road signs.
- [War mechs under twin suns (Hailuo 2.3)](https://aivideoatlas.com/shots/war-mechs-under-twin-suns-hailuo-2-3-ludoviccreator/): A tracking prompt that follows one mech's heavy stride across a desert battlefield.
- [Zero-gravity orbital greenhouse (Luma Ray 3)](https://aivideoatlas.com/shots/zero-gravity-orbital-greenhouse-luma-ray-3-ludoviccreator/): A floating-camera prompt through glowing alien plants in an orbital lab as a researcher works.
- [An anime tracking shot across a floating sky bridge](https://aivideoatlas.com/shots/mage-crossing-a-floating-sky-bridge-hailuo-2-3-ludoviccreator/): Prompted Hailuo 2.3 to track a mage across a rune-lit stone bridge between sky islands.
- [A burning-city mech clash from a one-sentence drone prompt](https://aivideoatlas.com/shots/mech-battle-overhead-drone-shot-luma-ray-3-ludoviccreator/): Used a single sentence in Luma Ray 3: two armoured mechs fight in a burning city, seen from an overhead drone.
- [A nature-doc chase: eagle banks through lava fountains](https://aivideoatlas.com/shots/eagle-escaping-an-erupting-volcano-luma-ray-3-ludoviccreator/): Prompted Luma Ray 3 for a fast rising follow shot on an eagle escaping ash and lava.
- [An FPV title reveal where ice shards spell a word](https://aivideoatlas.com/shots/text-vfx-word-forms-from-glacier-shards-runway-gen-4-5-charaspowerai/): Prompted Runway Gen-4.5 for a hyperspeed FPV run through a collapsing glacier where shards line up as "FROST" and shatter.
- [Sunset reunion love story (Kling 3.0)](https://aivideoatlas.com/shots/sunset-reunion-love-story-kling-3-0-navi-ai2/): A scene-by-scene prompt for a 15-second emotional reunion at sunset on a quiet golden-lit street.
- [An anime scooter chase weaving through Tokyo food stalls](https://aivideoatlas.com/shots/anime-scooter-chase-through-tokyo-luma-ray-3-ludoviccreator/): Prompted Luma Ray 3 for a low, fast tracking shot through alleys and stalls in anime style.
- [An overhead fantasy battle with arrow volleys and flying beasts](https://aivideoatlas.com/shots/fantasy-armies-and-glowing-arrows-overhead-hailuo-2-3-ludoviccreator/): Prompted Hailuo 2.3 for a top-down war scene with glowing arrows, siege magic and flying creatures.
- [Low-angle desert motorcycle at dawn (Hailuo 2.3)](https://aivideoatlas.com/shots/low-angle-desert-motorcycle-at-dawn-hailuo-2-3-ludoviccreator/): A low tracking prompt with dust trails, heat shimmer and long dawn shadows.
- [Knight with molten armor, three-shot sequence (Kling)](https://aivideoatlas.com/shots/knight-with-molten-armor-three-shot-sequence-kling-charaspowerai/): A multi-shot prompt written as a shot list: a wide battlefield, a close-up as lava-like cracks spread across the armor, then a wide walk through rising flames.
- [Text VFX: word from cracked desert earth (Runway Gen-4.5)](https://aivideoatlas.com/shots/text-vfx-word-from-cracked-desert-earth-runway-gen-4-5-charaspowerai/): A ground-skimming prompt where dust from opening fissures locks into the word "DRY" and then collapses.
- [Skateboard rail grind POV (Hailuo 2.3)](https://aivideoatlas.com/shots/skateboard-rail-grind-pov-hailuo-2-3-ludoviccreator/): A first-person skatepark prompt with camera shake on landings and sparks off the rail.
- [Orbit shot sunset duel with kanji shockwaves (Hailuo 2.3)](https://aivideoatlas.com/shots/orbit-shot-sunset-duel-with-kanji-shockwaves-hailuo-2-3-ludoviccreator/): A compact orbit-camera prompt for a stylised duel where each clash sends kanji rippling into the sky.
- [Lava-lit underworld throne room (Luma Ray 3)](https://aivideoatlas.com/shots/lava-lit-underworld-throne-room-luma-ray-3-ludoviccreator/): An overhead gliding prompt over a demon king's court with molten rivers and obsidian columns.
- [Drone orbit of a drifting sports car (Hailuo 2.3)](https://aivideoatlas.com/shots/drone-orbit-of-a-drifting-sports-car-hailuo-2-3-ludoviccreator/): A sweeping circling-drone prompt around a car drifting through mountain curves at sunset.
- [Japanese rooftop sunset timelapse (Luma Ray 3)](https://aivideoatlas.com/shots/japanese-rooftop-sunset-timelapse-luma-ray-3-ludoviccreator/): A locked-off wide timelapse prompt over an old Japanese neighbourhood as golden hour turns to neon night.
- [Upside-down forest walk (Luma Ray 3)](https://aivideoatlas.com/shots/upside-down-forest-walk-luma-ray-3-ludoviccreator/): A surreal follow-cam prompt through a forest with inverted trees and leaves that change colour with each step.
- [Text VFX: word forms in valley fog (Runway Gen-4.5)](https://aivideoatlas.com/shots/text-vfx-word-forms-in-valley-fog-runway-gen-4-5-charaspowerai/): A slow, quiet title-reveal prompt where morning mist reshapes into "BEGIN" and dissolves.
- [Text VFX: word ignites in a fire vortex (Runway Gen-4.5)](https://aivideoatlas.com/shots/text-vfx-word-ignites-in-a-fire-vortex-runway-gen-4-5-charaspowerai/): A punch-through-flames prompt where fire spirals into a vortex that ignites "INFERNO" and then explodes.
- [Monk at sunrise on a misty cliff (Luma Ray 3)](https://aivideoatlas.com/shots/monk-at-sunrise-on-a-misty-cliff-luma-ray-3-ludoviccreator/): A calm push-in from behind a meditating monk as the sun rises over mist-filled valleys.
- [Shrine maiden on a storm cliff, ink-brush style (Hailuo 2.3)](https://aivideoatlas.com/shots/shrine-maiden-on-a-storm-cliff-ink-brush-style-hailuo-2-3-ludoviccreator/): A low-angle prompt with exaggerated robe motion and lightning drawn in thick ink-brush strokes.
- [Desert-noir drone shot of a classic car (Hailuo 2.3)](https://aivideoatlas.com/shots/desert-noir-drone-shot-of-a-classic-car-hailuo-2-3-ludoviccreator/): An overhead follow prompt with a blood-red sunset and a lone motel on the horizon.
- [Bioluminescent exoplanet ocean (Kling 2.6)](https://aivideoatlas.com/shots/bioluminescent-exoplanet-ocean-kling-2-6-alin-reaper05/): A short sci-fi prompt with glowing sea life, twin moons in time-lapse and an underwater camera glide.
- [Pastel rooftop sunset, watercolour anime (Luma Ray 3)](https://aivideoatlas.com/shots/pastel-rooftop-sunset-watercolour-anime-luma-ray-3-ludoviccreator/): A gentle push-in with lens flares, drifting petals and watercolour tones for a dreamy anime rooftop scene.
- [FPV flight through Persepolis (Veo 3.1)](https://aivideoatlas.com/shots/fpv-flight-through-persepolis-veo-3-1-shushant-l/): A fast FPV prompt sweeping through Achaemenid palaces, columns and reliefs, with motion blur.
- [Text VFX: word in a volcanic lightning storm (Runway Gen-4.5)](https://aivideoatlas.com/shots/text-vfx-word-in-a-volcanic-lightning-storm-runway-gen-4-5-charaspowerai/): A prompt that pierces ash clouds above an eruption, where sparks and static briefly form "FURY".
- [Tilt-shift ships over a futuristic city (Runway Gen-4.5)](https://aivideoatlas.com/shots/tilt-shift-ships-over-a-futuristic-city-runway-gen-4-5-captainhahaa/): A tilt-shift prompt where a narrow focus band on passing ships makes the city below look like a miniature.
- [FPV flight through the ancient Lydian Kingdom (Veo 3.1)](https://aivideoatlas.com/shots/fpv-flight-through-the-ancient-lydian-kingdom-veo-3-1-shushant-l/): A fast FPV prompt weaving through temples, markets and coin workshops in ancient Sardis. It's part of a series of historical FPV flights.
- [Neon light burst over mountains (Runway Gen-4.5)](https://aivideoatlas.com/shots/neon-light-burst-over-mountains-runway-gen-4-5-jerrod-lew/): A short abstract prompt: a small neon circle in darkness explodes into waves that silhouette mountains.
- [Neon maglev tunnel sprint (Luma Ray 3)](https://aivideoatlas.com/shots/neon-maglev-tunnel-sprint-luma-ray-3-ludoviccreator/): A breakneck side-tracking prompt with a pilot chased by drones through a streaking neon tunnel.
- [Night train station with parallax (Luma Ray 3)](https://aivideoatlas.com/shots/night-train-station-with-parallax-luma-ray-3-ludoviccreator/): An anime medium shot with background parallax, wet platform reflections and glowing vending machines.
- [Blowtorch on salmon macro physics test (Veo 3.1)](https://aivideoatlas.com/shots/blowtorch-on-salmon-macro-physics-test-veo-3-1-va1enti-ai/): A locked-off macro prompt that tests whether a blowtorch flame hits and spreads across food realistically, with lighting and film stock spelled out.
- [Rainy-night urban thriller walk (Seedance 2.5)](https://aivideoatlas.com/shots/rainy-night-urban-thriller-walk-seedance-2-5-rachses2/): A 30-second suspense prompt that follows a woman from a subway exit through rain-soaked streets, beat by beat.
- [POV horse ride through the ancient Kuru Kingdom (Veo 3.1)](https://aivideoatlas.com/shots/pov-horse-ride-through-the-ancient-kuru-kingdom-veo-3-1-shushant-l/): A rider's-eye POV prompt galloping through an ancient Indian kingdom, with the horse's head and reins in frame.
- [Subway platform shot with a locked character reference (Kling)](https://aivideoatlas.com/shots/subway-platform-shot-with-a-locked-character-reference-kling-prometheanaix/): A reference-locked prompt that keeps one character's face, outfit and proportions identical in a realistic subway platform scene. The creator built the…
- [Anime power-up leap with lightning (Luma Ray 3)](https://aivideoatlas.com/shots/anime-power-up-leap-with-lightning-luma-ray-3-ludoviccreator/): A dynamic-angle prompt with speed lines and exaggerated perspective, ending in a lightning-filled leap.
- [Rotating beverage can with floating fruit (Kling 2.6)](https://aivideoatlas.com/shots/rotating-beverage-can-with-floating-fruit-kling-2-6-kanishkhaai/): An image-to-video product prompt: a can rotates 360° while the camera orbits and fruit pieces float through frame.
- [Extreme close-up miniature sushi character (Kling)](https://aivideoatlas.com/shots/extreme-close-up-miniature-sushi-character-kling-leelinai123/): A detailed macro prompt: handheld extreme close-up with a slow push-in on a tiny anthropomorphic sushi character. It's a good model for breathing-camera micro…
- [Moonlit rooftop chase in slow motion (Luma Ray 3)](https://aivideoatlas.com/shots/moonlit-rooftop-chase-in-slow-motion-luma-ray-3-ludoviccreator/): An anime slow-motion side shot of a robed girl fleeing shadow spirits, her staff leaving a light trail.
- [Dragon in a storm: same-prompt test across four models](https://aivideoatlas.com/shots/dragon-in-a-storm-same-prompt-test-across-four-models-tianjinxiin/): An epic fantasy prompt with a dragon in lightning-lit clouds and a sweeping camera, used as a stress test for physics, volumetric light and camera movement.
- [Warehouse fight storyboard: Seedance 2.0 vs Kling V3 Pro](https://aivideoatlas.com/shots/warehouse-fight-storyboard-seedance-2-0-vs-kling-v3-pro-aibabbler/): A long storyboard-style prompt for a crime-drama fight in a dim warehouse, written to test action choreography.
- [Magical-girl transformation spin (Luma Ray 3)](https://aivideoatlas.com/shots/magical-girl-transformation-spin-luma-ray-3-ludoviccreator/): An orbiting-camera prompt for an anime transformation with crystals, ribbons of light and energy wings.
- [Rainstorm golf shot physics test](https://aivideoatlas.com/shots/rainstorm-golf-shot-physics-test-noman23761/): A brutal physics prompt (a golfer driving off a cliff tee in a violent rainstorm) designed to test ball tracking and weather.
- [Slow-motion walking shot with Kling 3.0 Motion Control](https://aivideoatlas.com/shots/slow-motion-walking-shot-with-kling-3-0-motion-control-dilshadai1/): A one-line cinematic prompt for a slow-motion walk with dramatic lighting, run through Kling 3.0 Motion Control on a phone.
- [POV bike ride into ancient Kosala (Veo 3.1)](https://aivideoatlas.com/shots/pov-bike-ride-into-ancient-kosala-veo-3-1-kisalay/): A first-person bicycle ride toward a fortified ancient Indian city with period architecture.
- [Chameleon colour shift, slow zoom (Runway Gen-4.5)](https://aivideoatlas.com/shots/chameleon-colour-shift-slow-zoom-runway-gen-4-5-curieuxexplore/): An image-to-video nature prompt with a slow zoom as a chameleon's skin shifts through vivid colours.
- [Girl on a bike with her dog (Kling 2.6)](https://aivideoatlas.com/shots/girl-on-a-bike-with-her-dog-kling-2-6-vibefowl/): A simple suburban prompt (child on a bicycle, colourful outfit, a Jack Russell running alongside) that's handy for testing character detail.
- [Low-angle cyclist tracking shot on a mountain road (Veo 3.1)](https://aivideoatlas.com/shots/low-angle-cyclist-tracking-shot-on-a-mountain-road-veo-3-1-sourajitsaha17/): A tracking-shot prompt where the camera follows a cyclist's curve down a foggy, wet mountain road with spray and sun flashes.
- [Neon city character turn (Kling 3.0 Motion Control)](https://aivideoatlas.com/shots/neon-city-character-turn-kling-3-0-motion-control-dilshadai1/): A short prompt for a character turning toward camera in a neon-lit futuristic city, built for Kling 3.0 Motion Control.
- [Dark-fantasy samurai fight with locked characters (Seedance 2.0)](https://aivideoatlas.com/shots/dark-fantasy-samurai-fight-with-locked-characters-seedance-2-0xchainwiz/): A fast-cut samurai action prompt that defines its characters once and keeps them identical, with an explicit no-gore note.
- [25-shot dark-comedy 'video flow' (Seedance 2.5)](https://aivideoatlas.com/shots/25-shot-dark-comedy-video-flow-seedance-2-5-nicuks/): An ambitious 15-second, 25-shot prompt written as a shot-by-shot flow with varied focal lengths and rapid editorial cuts.
- [Rainy anime heartbreak short (MiniMax H3)](https://aivideoatlas.com/shots/rainy-anime-heartbreak-short-minimax-h3-web3know/): A scene-timed vertical anime prompt for a short emotional story, starting with a rain scene at 0–5s.
- [12-shot anime rom-com classroom scene (Seedance 2.5)](https://aivideoatlas.com/shots/12-shot-anime-rom-com-classroom-scene-seedance-2-5-imhealmachine/): A vertical anime prompt that specifies exactly 12 shots and 11 cuts for a small classroom comedy beat. It's a good template for cut control.
- [GoPro shot from a helicopter over a lava field (Seedance 2.5)](https://aivideoatlas.com/shots/gopro-shot-from-a-helicopter-over-a-lava-field-seedance-2-5-ruslanchain/): A comedic vertical action-cam prompt filmed from a hovering helicopter doorway above a lava field.
- [Top-down pastel domino spiral (LTX 2.5 Pro)](https://aivideoatlas.com/shots/top-down-pastel-domino-spiral-ltx-2-5-pro-art-sweetyvig/): A satisfying top-down push-in prompt with hundreds of pastel dominoes toppling in slow motion.
- [Two-reference character shot, first take (Seedance 2.5)](https://aivideoatlas.com/shots/two-reference-character-shot-first-take-seedance-2-5-scenario-gg/): A prompt that maps @image1 (full body) and @image2 (close-up) to one character for 30 seconds at 720p.
- [cinematic-video-prompt-skill](https://aivideoatlas.com/shots/cinematic-video-prompt-skill-rylaispirit/): A cheat sheet and Claude skill covering camera angles, moves, lighting, composition and grading terms for video prompts.
- [awesome-ad-video-prompts](https://aivideoatlas.com/shots/awesome-ad-video-prompts-lichamnesia/): A curated set of original, high-craft prompts for product and ad videos, written for Seedance 2.0, Veo 3, Kling and Runway.
- [Descending drone shot over a flooded city (Veo)](https://aivideoatlas.com/shots/descending-drone-shot-over-a-flooded-city-veo-buildwithras/): An aerial prompt slowly descending through fog over a flooded historic European city with rescue boats, in an ash-grey IMAX look.
- [DirectorSKILL](https://aivideoatlas.com/shots/directorskill-wuwangzhang1/): A Claude Code skill for shot lists and keyframe/video prompts, with ten selectable director-style overlays.
- [ai-shortfilm-prompts](https://aivideoatlas.com/shots/ai-shortfilm-prompts-jnmetacode/): A Claude Code skill that turns a rough idea into a structured, model-ready video prompt, with 21 genre templates.
- [ai-media-generator](https://aivideoatlas.com/shots/ai-media-generator-hao0321/): A Claude Code skill that drafts director-style prompts for image, video and music and can run them in a browser.
- [visual-skills](https://aivideoatlas.com/shots/visual-skills-smixs/): Agent skills that pair film-craft ideas (blocking, montage) with exact prompt syntax for Seedance, Kling, Veo and others.
- [Rain-freeze samurai dolly-in (Seedance 2.0)](https://aivideoatlas.com/shots/rain-freeze-samurai-dolly-in-seedance-2-0-framefutura/): A short, comma-list prompt for a samurai drawing his sword in heavy rain while the droplets freeze mid-air, with a slow dolly-in and desaturated grade.
- [Steadicam night-market walk (LTX-2, local)](https://aivideoatlas.com/shots/steadicam-night-market-walk-ltx-2-local-rafacrackyt/): A 15-second Steadicam prompt moving through a Southeast Asian night market, run locally on LTX-2.
- [Misty valley sunrise drone shot (LTX-2, local)](https://aivideoatlas.com/shots/misty-valley-sunrise-drone-shot-ltx-2-local-rafacrackyt/): An aerial drone prompt over a misty mountain valley at sunrise with a forward glide.
- [awesome-seedance-2-prompts](https://aivideoatlas.com/shots/awesome-seedance-2-prompts-youmind-open/): A curated library of Seedance 2.0 prompts by style, plus notes on API use and keeping characters consistent.
- [awesome-seedance](https://aivideoatlas.com/shots/awesome-seedance-zerolu/): A large community collection of Seedance 2.0 prompts and resources across film, anime, UGC and ad styles.
- [awesome-video-prompts](https://aivideoatlas.com/shots/awesome-video-prompts-songguoxs/): A prompt collection for Veo 3/3.1, Kling and Hailuo, organised by scene type.

## Guides
- [Seedance (ByteDance Seed)](https://aivideoatlas.com/guides/seedance-bytedance-seed/): ByteDance Seed's official home for the Seedance video models. Start here for official release notes and demos before you pick a hosted…
- [Seedance 1.0 Pro on fal](https://aivideoatlas.com/guides/seedance-1-0-pro-on-fal/): fal's hosted image-to-video endpoint for Seedance 1.0 Pro, ByteDance's higher-quality tier. You can call it by API without running the…
- [Seedance 1.0 Lite on fal](https://aivideoatlas.com/guides/seedance-1-0-lite-on-fal/): The cheaper, faster Lite tier of Seedance 1.0 on fal, for text-to-video. The page lists 5 or 10 second clips at up to 720p.
- [Kling AI](https://aivideoatlas.com/guides/kling-ai/): Kuaishou's own Kling studio, where you make text-, image- and reference-driven video and images in one web app. It's the place to try new…
- [Kling 2.1 Master on fal](https://aivideoatlas.com/guides/kling-2-1-master-on-fal/): The premium Kling 2.1 Master endpoint on fal, for text-to-video. fal pitches it for the smoothest motion and closest prompt adherence of…
- [Kling 2.1 Standard on fal](https://aivideoatlas.com/guides/kling-2-1-standard-on-fal/): A lower-cost Kling 2.1 image-to-video endpoint on fal. fal's page gives a clear per-clip and per-second price, which makes it easy to…
- [Veo (Google DeepMind)](https://aivideoatlas.com/guides/veo-google-deepmind/): Google DeepMind's page for the Veo video model family, with capability notes and sample clips straight from the lab.
- [Veo 3 on fal](https://aivideoatlas.com/guides/veo-3-on-fal/): Veo 3 served through fal's API, with text-to-video and optional generated audio. Price depends on whether audio is on.
- [Veo 3 Fast on fal](https://aivideoatlas.com/guides/veo-3-fast-on-fal/): A faster, cheaper Veo 3 variant on fal. It's a sensible default for drafts before you spend on the full model.
- [Veo on Gemini API docs](https://aivideoatlas.com/guides/veo-on-gemini-api-docs/): Google's developer docs for generating video through the Gemini API, including when to pick Veo 3.1 versus faster editing-oriented models.
- [Google Flow](https://aivideoatlas.com/guides/google-flow/): Google's filmmaking app built on Veo and its image models. You assemble shots and scenes in one place instead of generating clips one by…
- [Runway](https://aivideoatlas.com/guides/runway/): Runway's main site: a web studio and API for generating and editing video with its Gen-series models.
- [Runway pricing](https://aivideoatlas.com/guides/runway-pricing/): Runway's plan page (Free, Standard, Pro, Max), credit-based. Check it before estimating per-clip costs, since credits per second vary by…
- [Runway API docs](https://aivideoatlas.com/guides/runway-api-docs/): Developer docs for Runway's API: auth, endpoints and model options for building video generation into your own product.
- [Runway Changelog](https://aivideoatlas.com/guides/runway-changelog/): Runway's running log of releases. It's the quickest way to see which models, clip lengths and features are new.
- [Hailuo AI](https://aivideoatlas.com/guides/hailuo-ai/): MiniMax's consumer app for its Hailuo video models, with text- and image-to-video plus social-oriented tools.
- [MiniMax Hailuo 02 on fal](https://aivideoatlas.com/guides/minimax-hailuo-02-on-fal/): Hailuo 02 image-to-video through fal, billed per second at 512p or 768p.
- [MiniMax video API docs](https://aivideoatlas.com/guides/minimax-video-api-docs/): MiniMax's platform overview, where to find API access for its video, speech and language models.
- [Luma Dream Machine](https://aivideoatlas.com/guides/luma-dream-machine/): Luma's Dream Machine app for its Ray video models. It runs on credit-based monthly plans.
- [Luma Ray2 on fal](https://aivideoatlas.com/guides/luma-ray2-on-fal/): Luma Ray 2 through fal's API. It's known for natural motion and coherent scenes, and fal's page quotes the cost per 5-second clip.
- [Luma API docs](https://aivideoatlas.com/guides/luma-api-docs/): Luma's API reference, for calling Ray video generation directly rather than through a reseller.
- [Pika](https://aivideoatlas.com/guides/pika/): Pika's creator-focused video app, with short effects-driven clips and multi-shot generation.
- [Pika 2.2 on fal](https://aivideoatlas.com/guides/pika-2-2-on-fal/): Pika 2.2 text-to-video on fal, at up to 1080p. fal lists a per-video price range.
- [fal video models](https://aivideoatlas.com/guides/fal-video-models/): fal's catalog of hosted video models (Kling, Veo, Seedance, Wan, Hailuo and more) behind a single API. It's useful for switching models…
- [Replicate video collection](https://aivideoatlas.com/guides/replicate-video-collection/): Replicate's curated collection of text-to-video models you can run by API, an alternative host to fal.
- [ComfyUI](https://aivideoatlas.com/guides/comfyui/): ComfyUI is the open, node-based app for building image and video pipelines on your own GPU or in the cloud. Most open-model video…
- [ComfyUI docs: video](https://aivideoatlas.com/guides/comfyui-docs-video/): Official ComfyUI tutorial for Wan 2.1: text-to-video with the 1.3B model and image-to-video with the 14B model, including where each model…
- [ComfyUI Changelog](https://aivideoatlas.com/guides/comfyui-changelog/): ComfyUI's release log. Check it to see when new video models get native nodes.
- [Wan 2.1 on fal](https://aivideoatlas.com/guides/wan-2-1-on-fal/): Wan 2.1 image-to-video hosted on fal, with roughly 5–6 second clips at 480p or 720p and a flat price per video.
- [Wan (Alibaba) GitHub](https://aivideoatlas.com/guides/wan-alibaba-github/): Alibaba's official open-weights repo for Wan 2.1, with code, model downloads and hardware notes for running it locally.
- [LTX Video on fal](https://aivideoatlas.com/guides/ltx-video-on-fal/): Lightricks' open LTX Video model on fal. It's one of the cheapest hosted options, at a flat per-video price.
- [HunyuanVideo on fal](https://aivideoatlas.com/guides/hunyuanvideo-on-fal/): Tencent's open HunyuanVideo on fal, at a flat per-video price. fal notes it's free for commercial use.
- [Higgsfield](https://aivideoatlas.com/guides/higgsfield/): Higgsfield is a creator platform that wraps several video and image models with camera-move presets, editing, upscaling and an agent for…
- [Hedra](https://aivideoatlas.com/guides/hedra/): Hedra's platform and models, best known for expressive character and talking-avatar video.
- [Moonvalley Marey](https://aivideoatlas.com/guides/moonvalley-marey/): Moonvalley, the lab behind the Marey video model, which it positions for professional film work.
- [Vidu](https://aivideoatlas.com/guides/vidu/): Shengshu's Vidu video generator, with text-, image- and reference-to-video aimed at social content and ads.
- [PixVerse](https://aivideoatlas.com/guides/pixverse/): PixVerse's video generation models and app, now also pushing into real-time and interactive video.
- [Krea Video](https://aivideoatlas.com/guides/krea-video/): Krea's creative suite, which gives you access to several third-party video models (including Seedance) alongside its own image tools.
- [Topaz Video AI](https://aivideoatlas.com/guides/topaz-video-ai/): Topaz's video enhancement models for upscaling, sharpening, stabilizing and frame interpolation. It's a common last step before delivering…
- [ElevenLabs](https://aivideoatlas.com/guides/elevenlabs/): ElevenLabs' voice generation platform, the usual pick for narration and character voices in AI video pipelines.
- [Veo prompt guide (Google Cloud)](https://aivideoatlas.com/guides/veo-prompt-guide-google-cloud/): Google Cloud's official prompting guide for Veo, covering how to describe subject, action, camera, style and audio to get more…
- [Veo 3.1 on fal](https://aivideoatlas.com/guides/veo-3-1-on-fal/): Veo 3.1 on fal for text-to-video. fal lists separate per-second prices with and without audio, plus a higher 4K tier.
- [Veo 3.1 Fast on fal](https://aivideoatlas.com/guides/veo-3-1-fast-on-fal/): The fast Veo 3.1 tier on fal, at roughly half the price of full Veo 3.1 per second. It's a good fit for iterating before a final render.
- [Kling 2.5 Turbo Pro on fal](https://aivideoatlas.com/guides/kling-2-5-turbo-pro-on-fal/): Kling 2.5 Turbo Pro text-to-video on fal, Kling's speed-optimised premium tier. The price wasn't captured from the page.
- [Hailuo 2.3 Pro on fal](https://aivideoatlas.com/guides/hailuo-2-3-pro-on-fal/): MiniMax Hailuo 2.3 Pro image-to-video on fal at 1080p, billed at a flat price per generation.
- [Wan 2.5 Preview on fal](https://aivideoatlas.com/guides/wan-2-5-preview-on-fal/): A preview of Wan 2.5 text-to-video on fal, with per-second prices that rise from 480p to 1080p. The page also accepts an audio file input.
- [LTX-2 on fal](https://aivideoatlas.com/guides/ltx-2-on-fal/): Lightricks' LTX-2 Pro on fal: text-to-video with audio from 1080p up to 2160p, billed per second by resolution.
- [Wan 2.2 on GitHub](https://aivideoatlas.com/guides/wan-2-2-on-github/): Alibaba's official open-weights repo for Wan 2.2, the successor to 2.1, with code and model downloads for local runs.
- [LTX-2 on GitHub](https://aivideoatlas.com/guides/ltx-2-on-github/): Lightricks' official Python inference package and LoRA trainer for LTX-2, its open audio-video model.
- [ComfyUI-VideoHelperSuite](https://aivideoatlas.com/guides/comfyui-videohelpersuite-kosinkadink/): Nodes for loading, combining and exporting video frames in ComfyUI. Nearly every ComfyUI video workflow depends on it.
- [ComfyUI-MiniMaxH3-Easy](https://aivideoatlas.com/guides/comfyui-minimaxh3-easy-nkxx188/): A single compact ComfyUI workflow for MiniMax H3 that covers text-to-video, image-to-video, first/last-frame and reference video, with one…
- [comfyui-mcp](https://aivideoatlas.com/guides/comfyui-mcp-artokun/): An MCP server plus sidebar agent that lets an AI assistant build, run and edit ComfyUI graphs in plain language, for images, video and…
- [Vibe-Workflow](https://aivideoatlas.com/guides/vibe-workflow-samuraigpt/): An open-source, node-based builder for chaining image and video generation steps, pitched as a free alternative to Weavy and Krea Nodes.
- [awesome-ltx2](https://aivideoatlas.com/guides/awesome-ltx2-wildminder/): A maintained index of LTX-2 models, text encoders, LoRAs and ComfyUI workflows in one place.
- [velorn](https://aivideoatlas.com/guides/velorn-velornlabs/): An AI-native video editor organised around a real timeline, with generative steps and local agent control.
- [Mix-Studio](https://aivideoatlas.com/guides/mix-studio-blackmixture/): A polished front-end that runs tuned ComfyUI image and video workflows from desktop or phone without touching the node graph.
- [ComfyUI-H3-Motion-Context-MultiRef](https://aivideoatlas.com/guides/comfyui-h3-motion-context-multiref-seitanism/): MiniMax H3 nodes and workflows for extending clips, one-shot music videos, video-to-video motion transfer and custom keyframes.
- [ComfyUI-Easy-Media](https://aivideoatlas.com/guides/comfyui-easy-media-yolain/): ComfyUI nodes that simplify loading media and assembling video pipelines, with friendlier parameters than the defaults.
- [Goohai-MiniMax-H3_Integration](https://aivideoatlas.com/guides/goohai-minimax-h3-integration-goohai/): ComfyUI nodes for MiniMax H3's audio-video conditioning and reference-driven generation.
- [ComfyUI-WanVideoWrapper](https://aivideoatlas.com/guides/comfyui-wanvideowrapper-kijai/): Kijai's widely used ComfyUI wrapper for Wan video models. New Wan features and optimisations often land here before native nodes.
- [ComfyUI-WanVideoStartEndFrames](https://aivideoatlas.com/guides/comfyui-wanvideostartendframes-raindrop313/): Nodes to generate a Wan 2.1 clip between a chosen first and last frame, built on a modified Kijai wrapper.
- [ComfyUI-Bernini](https://aivideoatlas.com/guides/comfyui-bernini-aimixer/): A standalone ComfyUI plugin for the Wan 2.2 Bernini model, for generating and editing video.
- [ComfyUI-PainterLongVideo](https://aivideoatlas.com/guides/comfyui-painterlongvideo-princepainte/): A ComfyUI node for long-form Wan 2.2 videos that keeps motion and scenes consistent and corrects unwanted slow motion.
- [ComfyUI-Wan-VACE-Video-Joiner](https://aivideoatlas.com/guides/comfyui-wan-vace-video-joiner-stuttlepress/): Workflows that use Wan VACE to build smooth transitions between any two clips, AI-generated or real footage.
- [ComfyUI-Wan-VACE-Prep](https://aivideoatlas.com/guides/comfyui-wan-vace-prep-stuttlepress/): Helper nodes that make common edits (transitions, extensions, outpainting) easier to set up for Wan VACE.
- [ComfyUI-Wan-SVI2Pro-FLF](https://aivideoatlas.com/guides/comfyui-wan-svi2pro-flf-well-made/): Nodes for Wan 2.2 SVI 2 Pro that add first/last-frame keyframe control and seamless stitching across clips.
- [wavespeed-comfyui](https://aivideoatlas.com/guides/wavespeed-comfyui-wavespeedai/): WaveSpeed's ComfyUI nodes for calling hundreds of hosted image and video models (Seedance, Wan and others) inside a local graph.
- [ComfyUI-AnimateDiff-Evolved](https://aivideoatlas.com/guides/comfyui-animatediff-evolved-kosinkadink/): The improved AnimateDiff implementation for ComfyUI with advanced sampling. It's the backbone of most AnimateDiff-era workflows.
- [ComfyUI-Cloud](https://aivideoatlas.com/guides/comfyui-cloud-nathannlu/): Runs local ComfyUI workflows on cloud GPUs when your machine lacks the VRAM.
- [ComfyUI-ADMotionDirector](https://aivideoatlas.com/guides/comfyui-admotiondirector-kijai/): Nodes for training AnimateDiff motion LoRAs inside ComfyUI.
- [comfyui-dream-video-batches](https://aivideoatlas.com/guides/comfyui-dream-video-batches-alt-key-proj/): Nodes for batch video generation with SVD and AnimateDiff.
- [ComfyUI-HunyuanVideoWrapper](https://aivideoatlas.com/guides/comfyui-hunyuanvideowrapper-kijai/): Kijai's ComfyUI wrapper for Tencent's HunyuanVideo, an early way to run it locally with memory optimisations.
- [ComfyUI-HunyuanLoom](https://aivideoatlas.com/guides/comfyui-hunyuanloom-logtd/): Nodes for editing existing videos with HunyuanVideo (video-to-video) in ComfyUI.
- [ComfyUI_HunyuanVideoFoley](https://aivideoatlas.com/guides/comfyui-hunyuanvideofoley-if-ai/): Generates matching sound effects for a video from the clip plus a text prompt, using HunyuanVideo-Foley in ComfyUI.
- [ComfyUI-HunyuanVideoMultiLora](https://aivideoatlas.com/guides/comfyui-hunyuanvideomultilora-facok/): ComfyUI nodes for stacking several LoRAs on HunyuanVideo at once.
- [DJZ-Workflows](https://aivideoatlas.com/guides/djz-workflows-mushroomflee/): A large library of ready-made ComfyUI workflows across image and video models, including Hunyuan and CogVideo.
- [ComfyUI-TeaCacheHunyuanVideo](https://aivideoatlas.com/guides/comfyui-teacachehunyuanvideo-facok/): Applies the TeaCache caching trick to HunyuanVideo in ComfyUI to speed up generation.
- [ComfyUI-HunyuanVideo-Nyan](https://aivideoatlas.com/guides/comfyui-hunyuanvideo-nyan-zer0int/): Nodes that let you scale how strongly the CLIP and LLM text encoders steer HunyuanVideo, for tighter prompt control.
- [ComfyUI-LTXVideo](https://aivideoatlas.com/guides/comfyui-ltxvideo-lightricks/): Lightricks' official ComfyUI support for LTX-Video, the reference way to run LTX models in a graph.
- [ComfyUI-LTXTricks](https://aivideoatlas.com/guides/comfyui-ltxtricks-logtd/): Extra ComfyUI nodes that add finer control over LTX Video generation.
- [ComfyUI-PainterNodes](https://aivideoatlas.com/guides/comfyui-painternodes-princepainte/): A ComfyUI toolkit spanning video generation, image editing and audio-driven lip-sync across Flux, MiniMax, LTX and Wan 2.2.
- [comfyui-deno-custom-nodes](https://aivideoatlas.com/guides/comfyui-deno-custom-nodes-deno2026/): A grab-bag of ComfyUI nodes: RTX Video Super Resolution, LTX 2.3 helpers, Wan 2.2 reference editing, and video compare and preview.
- [ID-LoRA-LTX2.3-ComfyUI](https://aivideoatlas.com/guides/id-lora-ltx2-3-comfyui-id-lora/): A ComfyUI node for LTX 2.3 that makes video carrying one person's identity, from a reference image and voice. Use only with consent of the…
- [ComfyUI-PainterLTXV2](https://aivideoatlas.com/guides/comfyui-painterltxv2-princepainte/): Sampler and latent-prep nodes for LTXV that separate audio and video sampling.
- [LTX2-Infinity](https://aivideoatlas.com/guides/ltx2-infinity-z-l-d/): A ComfyUI workflow that chains LTX-2 generations into effectively unlimited-length video, based on the Stable-Video-Infinity idea.
- [higgsfield-ai-prompt-skill](https://aivideoatlas.com/guides/higgsfield-ai-prompt-skill-osidemedia/): A Claude skill bundle (32 sub-skills) for writing cinematic Higgsfield prompts, centred on Seedance 2.x features like omni-reference and…
- [lanshu-awesome-ai-video-kit](https://aivideoatlas.com/guides/lanshu-awesome-ai-video-kit-cclank/): A Chinese-language kit from enterprise video projects: hundreds of prompts across 15 models, Claude skills and methodology notes.
- [img-prompt](https://aivideoatlas.com/guides/img-prompt-rockbenben/): Pick tags in your own language and it assembles the English prompt that image and video models expect.
- [story-shot-agent](https://aivideoatlas.com/guides/story-shot-agent-neopen/): An agent that breaks a script into shots and writes consistent text-to-video prompts for each, keeping characters stable across segments.
- [vibe-creating-skill](https://aivideoatlas.com/guides/vibe-creating-skill-alisa0808/): A portable, bilingual agent skill that rewrites ideas into model-ready text-to-video prompts.
- [seedance2-skill](https://aivideoatlas.com/guides/seedance2-skill-dexhunter/): An agent skill focused only on writing strong Seedance 2.0 prompts.
- [awesome-seedance](https://aivideoatlas.com/guides/awesome-seedance-learnprompt/): A Seedance 2.x prompt library that traces cases to their original posts and publishes cross-model retest verdicts.
- [higgsfield-seedance2-jineng](https://aivideoatlas.com/guides/higgsfield-seedance2-jineng-beshuaxian/): Fifteen Claude prompt skills for Seedance 2.0 on Higgsfield, each built around a hook-first structure for genres like CGI, anime and ads.
- [ai-shortVideo-pipeline](https://aivideoatlas.com/guides/ai-shortvideo-pipeline-myccarl/): Backend plumbing for an AI short-video service: multi-model failover, metering and quality gating.
- [drama-skills](https://aivideoatlas.com/guides/drama-skills-zenstory-ai/): Open-source skills for producing AI short dramas: script, character assets, storyboards and image/video prompts, with review steps.
- [Maestro](https://aivideoatlas.com/guides/maestro-blizaine/): A fully local video, image and music studio on the WanGP pipeline. Its director mode plans a whole music video or short from one prompt.
- [Nomi](https://aivideoatlas.com/guides/nomi-aqm857886159/): An open-source video workbench that lets coding agents direct any model or local ComfyUI over MCP, from storyboard to an editable first cut.
- [flowboard](https://aivideoatlas.com/guides/flowboard-crisng95/): A local infinite-canvas tool where you wire model, product and scene nodes into product videos.
- [OpenMontage](https://aivideoatlas.com/guides/openmontage-calesthio/): An agentic video production system that gives AI coding assistants a set of pipelines, tools and production-knowledge files for making…
- [CogVideo](https://aivideoatlas.com/guides/cogvideo-zai-org/): The official repo for CogVideo and CogVideoX, the open text- and image-to-video models from Zhipu/THUDM.
- [LTX-Video](https://aivideoatlas.com/guides/ltx-video-lightricks/): Lightricks' official LTX-Video repo: open weights and inference code for one of the fastest open video models.
- [dramaclaw](https://aivideoatlas.com/guides/dramaclaw-dramaclaw/): A script-to-finished-film engine for dramas, ads and product videos, built as one end-to-end pipeline.
- [agnes-video-generator](https://aivideoatlas.com/guides/agnes-video-generator-lcy362/): A self-hosted web app that turns text into multi-scene videos with narration, subtitles and a presenter, powered by Agnes AI.
- [Open-AI-UGC](https://aivideoatlas.com/guides/open-ai-ugc-anil-matcha/): A self-hostable Next.js app for making UGC-style video ads with AI actors, using models like Veo 3.1 and Seedance 2. Disclose AI actors in…
- [openjourney](https://aivideoatlas.com/guides/openjourney-ammaarreshi/): A Midjourney-style web UI clone that generates images with Imagen 4 and video with Veo through Google's Gemini SDK.
- [AI-NovelFlow](https://aivideoatlas.com/guides/ai-novelflow-qzw881130/): A Chinese open-source platform that turns novels into videos by chaining open image and image-to-video models and community ComfyUI…
- [seedance-2-generator](https://aivideoatlas.com/guides/seedance-2-generator-samuraigpt/): A starter SaaS codebase (Next.js, Stripe, NextAuth, Prisma) for selling Seedance 2.x video generation.
- [ComfyUI-fal-API](https://aivideoatlas.com/guides/comfyui-fal-api-gokayfem/): ComfyUI nodes that call fal's 1,400+ hosted models, including Kling, Veo and Seedance, with caching and cost controls.
- [muapi-comfyui](https://aivideoatlas.com/guides/muapi-comfyui-samuraigpt/): ComfyUI nodes for 600+ hosted models, including Seedance, Kling and Veo 3, via the muapi.ai service.
- [awesome-MiniMax-H3-cases](https://aivideoatlas.com/guides/awesome-minimax-h3-cases-skynotsilent/): A large, traceable gallery of MiniMax/Hailuo H3 cases with their public prompts and checked tutorials, in two languages.
- [wind-comic](https://aivideoatlas.com/guides/wind-comic-chrischen667/): A multi-agent pipeline that turns a one-line idea into a short drama: script, storyboards and character-consistent video, with swappable…
- [egaki](https://aivideoatlas.com/guides/egaki-remorses/): A command-line tool for generating images and video from the terminal across Google, OpenAI, fal, Replicate and Seedance. Agents can use…
- [fal-mcp-server](https://aivideoatlas.com/guides/fal-mcp-server-luminarylane/): An MCP server that lets Claude generate images, video, music and audio through fal.
- [HunyuanVideo](https://aivideoatlas.com/guides/hunyuanvideo-tencent-huny/): Tencent's original open HunyuanVideo repo: weights, code and a technical report for a large open video model.
- [HunyuanVideo-1.5](https://aivideoatlas.com/guides/hunyuanvideo-1-5-tencent-huny/): HunyuanVideo 1.5, Tencent's lighter open video model aimed at running on more accessible hardware.
- [open-higgsfield](https://aivideoatlas.com/guides/open-higgsfield-wide-trace/): An open-source studio with one prompt bar, per-model settings and a single gallery of finished runs.
- [VGen](https://aivideoatlas.com/guides/vgen-ali-vilab/): Alibaba's VGen research codebase covering several diffusion video methods.
- [goku](https://aivideoatlas.com/guides/goku-saiyan-world/): Code for the Goku video generation foundation models, a CVPR 2025 highlight paper.
- [synergize-motion-appearance](https://aivideoatlas.com/guides/synergize-motion-appearance-shaelynz/): Official code for a CVPR 2025 paper on talking-head video generation with multi-scale codebooks. Research code; use only with consent of…
- [video2x](https://aivideoatlas.com/guides/video2x-k4yt3x/): A long-running open framework for AI video upscaling and frame interpolation, with several backends in one tool.
- [DAIN](https://aivideoatlas.com/guides/dain-baowenbo/): Depth-Aware Video Frame Interpolation (CVPR 2019), the classic research code.
- [ComfyUI-Frame-Interpolation](https://aivideoatlas.com/guides/comfyui-frame-interpolation-fannovel16/): ComfyUI nodes for frame interpolation (RIFE, FILM and others) to raise the frame rate of generated clips.
- [free-ai-video-upscaler](https://aivideoatlas.com/guides/free-ai-video-upscaler-sb2702/): Source for a free browser-based AI video upscaler.
- [TheAnimeScripter](https://aivideoatlas.com/guides/theanimescripter-nevermindnil/): An open anime-video toolkit for AI upscaling, RIFE interpolation and restoration in one pass, as CLI, standalone app or After Effects…
- [vapourkit](https://aivideoatlas.com/guides/vapourkit-kim2091/): A front-end for VapourSynth focused on video upscaling.
- [Lance – image/video generation and understanding in one model](https://aivideoatlas.com/guides/lance-image-video-generation-and-understanding-in-one-model-cleardusk/): Lance, from ByteDance, is a single model for both generating and understanding images and video, with code, paper and weights linked.
- [Veo 3 and Imagen 4, and a new tool for filmmaking called Flow](https://aivideoatlas.com/guides/veo-3-and-imagen-4-and-a-new-tool-for-filmmaking-called-flow-youssefarizk/): Google's announcement of Veo 3 with native audio, Imagen 4, and the Flow filmmaking app.
- [Runway Gen-4.5: A new frontier for video generation](https://aivideoatlas.com/guides/runway-gen-4-5-a-new-frontier-for-video-generation-meetpateltec/): Runway's announcement page for Gen-4.5, its next-generation video model.
- [A Pipeline for Making 10-minute AI Movies with Claude Code and Seedance](https://aivideoatlas.com/guides/a-pipeline-for-making-10-minute-ai-movies-with-claude-code-and-seedanc-dawndrain/): A Claude Code pipeline that makes 10-minute films with Claude as director, combining Seedance for video, Nano Banana for images and…
- [MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video](https://aivideoatlas.com/guides/minimax-h3-day-0-support-in-comfyui-open-weights-native-audio-and-2k-v-vblanco/): Comfy's post on day-one ComfyUI support for MiniMax H3: open weights, native audio and 2K video.
- [Text-to-video model from scratch (2 brothers, 2 years, 2B params)](https://aivideoatlas.com/guides/text-to-video-model-from-scratch-2-brothers-2-years-2b-params-schopra909/): Two brothers trained a 2B-parameter text-to-video model from scratch. Their write-up shows both good and bad samples.
- [WanX open weight sota 14B video model release](https://aivideoatlas.com/guides/wanx-open-weight-sota-14b-video-model-release-boredpositro/): The Hugging Face release of the open 14B Wan (WanX) video model.
- [LTX-Video: Realtime Video Latent Diffusion](https://aivideoatlas.com/guides/ltx-video-realtime-video-latent-diffusion-lnyan/): The arXiv paper behind LTX-Video, explaining how it generates video faster than real time.
- [LTXV 13B Distilled – Generate 5s Videos in Under 10s](https://aivideoatlas.com/guides/ltxv-13b-distilled-generate-5s-videos-in-under-10s-statusreport/): Lightricks' distilled LTXV 13B, a faster version of its open model.
- [I made an Image2Video version of HunyuanVideo and tonight I open-sourced it](https://aivideoatlas.com/guides/i-made-an-image2video-version-of-hunyuanvideo-and-tonight-i-open-sourc-aero-leap/): A community-built image-to-video variant of HunyuanVideo, released as open source on GitHub.
- [ManimGX – Manim's API on a Rust/wgpu engine, for 3D videos in Python](https://aivideoatlas.com/guides/manimgx-manim-s-api-on-a-rust-wgpu-engine-for-3d-videos-in-python-sinaatalay/): A re-implementation of the Manim animation API on a Rust/wgpu engine, for code-driven 2D/3D explainer videos in Python. It also runs in…
- [comfyui-vrgamedevgirl](https://aivideoatlas.com/guides/comfyui-vrgamedevgirl-vrgamegirl19/): A large ComfyUI node pack for AI video production. Its main tool, the AI Video Builder, plans, prompts, generates, reviews and assembles a…
- [ComfyUI-Spectrum-MiniMax-H3](https://aivideoatlas.com/guides/comfyui-spectrum-minimax-h3-xmarre/): ComfyUI nodes that apply Spectrum, a training-free sampling speed-up from a 2026 paper, to the native MiniMax H3 audio-video model. They…
- [ComfyUI-MiniMaxH3-TimelineDirector](https://aivideoatlas.com/guides/comfyui-minimaxh3-timelinedirector-songssx/): A ComfyUI plugin and all-in-one workflow for MiniMax H3. It covers text-to-video, reference images, audio-driven generation, editing and…
- [ComfyUI_MiniMax_H3_Extender](https://aivideoatlas.com/guides/comfyui-minimax-h3-extender-tritant/): A ComfyUI node that chains several MiniMax H3 clips into one long sequence, carrying motion, visuals and audio across the joins. Recent…
- [Calliope](https://aivideoatlas.com/guides/calliope-benjiyaya/): A local story-to-video app. It turns an idea into a storyline and script, splits scenes into shots, generates each shot through your own…
- [Comfyui-MMH3-UltimateUpscale](https://aivideoatlas.com/guides/comfyui-mmh3-ultimateupscale-bbaudio-2025/): A single ComfyUI node that upscales finished MiniMax H3 videos on low-VRAM GPUs by processing time chunks and spatial tiles. The audio…
- [comfy-skills](https://aivideoatlas.com/guides/comfy-skills-comfy-org/): Comfy's official plugin for coding agents. It adds slash commands and an MCP connection so an agent can generate images, video, audio and…
- [FastVideo](https://aivideoatlas.com/guides/fastvideo-hao-ai-lab/): An open framework for faster video generation, covering both post-training and real-time inference. Docs and a cookbook are linked from…
- [LightX2V](https://aivideoatlas.com/guides/lightx2v-modeltc/): A lightweight inference framework for text-to-video, image-to-video and image generation that supports several open models. There's also a…
- [vibeframe](https://aivideoatlas.com/guides/vibeframe-vericontext/): A CLI and MCP server that lets a coding agent turn a brief into a finished MP4 using your own Seedance, Runway, Kling or Gemini keys…
- [Director-style AI ad with Seedance 2.5 and Claude prompts (Higgsfield)](https://aivideoatlas.com/guides/director-style-ai-ad-with-seedance-2-5-and-claude-prompts-higgsfield-higgsfield-ai/): Higgsfield walks through a full commercial build: characters and locations made in Soul Cinema, assets refined in Seedream 5 Pro, shot…
- [One take, three camera angles with Seedance 2.5 (Higgsfield)](https://aivideoatlas.com/guides/one-take-three-camera-angles-with-seedance-2-5-higgsfield-higgsfield-ai/): Turns a single static take into high, low and Dutch-angle versions: draft the prompt with ChatGPT, then run the shot through Seedance 2.5…
- [Keyframes to full character animation in ComfyUI (Wan 2.2 FLF)](https://aivideoatlas.com/guides/keyframes-to-full-character-animation-in-comfyui-wan-2-2-flf-comfyui/): The official ComfyUI tutorial for in-betweening: you draw key poses, each consecutive pair runs through Wan 2.2's first-last-frame model…
- [Blender blockout as the blueprint for a ComfyUI video shot](https://aivideoatlas.com/guides/blender-blockout-as-the-blueprint-for-a-comfyui-video-shot-comfyui/): ComfyUI shows a 13-second anime fight where a simple Blender blockout fixes camera movement, character placement, attack paths and timing…
- [Build an ad studio app with Runway Dev and a coding agent](https://aivideoatlas.com/guides/build-an-ad-studio-app-with-runway-dev-and-a-coding-agent-runway/): Runway's walkthrough for turning one product photo into a social campaign: start from the Runway Dev quickstart, describe the app to a…
- [Ways to waste fewer credits on AI video generations (Curious Refuge)](https://aivideoatlas.com/guides/ways-to-waste-fewer-credits-on-ai-video-generations-curious-refuge-curious-refuge/): Curious Refuge shares the process it uses to avoid paying for bad generations on an AI film: set up checks before committing to full-cost…
- [Make a depth map with a free AI tool to guide AI video (Curious Refuge)](https://aivideoatlas.com/guides/make-a-depth-map-with-a-free-ai-tool-to-guide-ai-video-curious-refuge-curious-refuge/): A tutorial on creating depth maps with a free tool that runs locally on a Mac (or via fal.ai), then using the depth map as a reference to…
- [AI workflow for combining 2D animation with live action (Curious Refuge)](https://aivideoatlas.com/guides/ai-workflow-for-combining-2d-animation-with-live-action-curious-refuge-curious-refuge/): Curious Refuge and AI animation instructor Albert Bozesan show their current workflow for compositing 2D animated characters into…
- [Seamless over-the-top AI video intros, full workflow (MattVidPro)](https://aivideoatlas.com/guides/seamless-over-the-top-ai-video-intros-full-workflow-mattvidpro-mattvidpro/): MattVidPro shows his whole process for AI intros that blend into real footage. His intro prompt and Seedance 2.5 prompting guide are…
- [Using Claude Opus 5.5 in an AI video workflow (Tao Prompts)](https://aivideoatlas.com/guides/using-claude-opus-5-5-in-an-ai-video-workflow-tao-prompts-tao-prompts/): Tao Prompts covers where Claude Opus 5.5 fits in AI video production (use cases, then how to plug it into a generation workflow for…
- [Comfy Agent](https://aivideoatlas.com/guides/comfy-agent-comfyui/): ComfyUI's built-in agent plans, wires and debugs workflows on your canvas. Describe what you want to make and it connects the nodes and…
- [Higgsfield Katana (Claude Motion)](https://aivideoatlas.com/guides/higgsfield-katana-claude-motion-higgsfield-ai/): Higgsfield's video editing tool that runs inside Claude through the Higgsfield MCP: upload a reference and generate editable motion…
- [PixVerse Short Drama plugin](https://aivideoatlas.com/guides/pixverse-short-drama-plugin-pixverse/): A PixVerse plugin for AI agents: describe a scene in plain words and it handles planning and production through to a finished short-drama…
- [Low-VRAM character swap with MiniMax H3 in ComfyUI (no masking)](https://aivideoatlas.com/guides/low-vram-character-swap-with-minimax-h3-in-comfyui-no-masking-u-cgpixel23/): A ComfyUI workflow that swaps a character in a video using MiniMax H3 plus a Character Swap LoRA, with no masking. It renders at about…
- [LTX-2.5 (open weights)](https://aivideoatlas.com/guides/ltx-2-5-open-weights-lightricks/): Lightricks' open-weight LTX-2.5 checkpoint on Hugging Face. Per its tags: text-, image- and video-to-video plus joint audio-video…
- [MiniMax-H3 Turbo (LightX2V)](https://aivideoatlas.com/guides/minimax-h3-turbo-lightx2v-lightx2v/): Few-step Turbo LoRAs for the open MiniMax-H3 audio-video model from the LightX2V team, including an FL2V 8-step 768p LoRA. Reproduction…
- [MiniMax-H3 Turbo LoRA (larryvrh)](https://aivideoatlas.com/guides/minimax-h3-turbo-lora-larryvrh-larryvrh/): A LoRA for MiniMax-H3 that renders joint video and stereo audio in as few as 4 steps instead of about 20. The author recommends the v4…
- [FastH3 4-step preview (FastVideo)](https://aivideoatlas.com/guides/fasth3-4-step-preview-fastvideo-fastvideo/): A distilled MiniMax-H3 checkpoint from the FastVideo team (Hao AI Lab) that generates synchronised video and audio from text in four…
- [DMAD: 4-step MiniMax-H3 students](https://aivideoatlas.com/guides/dmad-4-step-minimax-h3-students-zhengmingyu/): A research release with 4-step distilled MiniMax-H3 students for joint audio-video generation, trained with DMAD (distribution matching as…
- [MiniMax-H3 Fun ControlNet Union 2.0 (Alibaba PAI)](https://aivideoatlas.com/guides/minimax-h3-fun-controlnet-union-2-0-alibaba-pai-alibaba-pai/): Version 2.0 of Alibaba PAI's union ControlNet for MiniMax-H3, which lets one model take several control signals to guide H3 video…
- [MiniMax-H3 Seamless Chain (multi-shot ComfyUI pack)](https://aivideoatlas.com/guides/minimax-h3-seamless-chain-multi-shot-comfyui-pack-joeygambino/): A ComfyUI node pack and two workflows that chain MiniMax-H3's roughly 10–15 second blocks into one continuous take, with no visible cuts…
- [LTX-2.3 / LTX-2.5 ComfyUI workflows (RuneXX)](https://aivideoatlas.com/guides/ltx-2-3-ltx-2-5-comfyui-workflows-runexx-runexx/): A collection of ComfyUI workflows for LTX-2.3 that the author says also work with LTX-2.5 models (with dedicated 2.5 workflows to follow)…
- [LongCat-Video (Meituan)](https://aivideoatlas.com/guides/longcat-video-meituan-meituan-longcat/): A 13.6B open video model that handles text-to-video, image-to-video and video continuation in one network. It is pretrained on…
- [MAGI-1 (Sand AI)](https://aivideoatlas.com/guides/magi-1-sand-ai-sand-ai/): An autoregressive video model that generates video chunk by chunk, which suits streaming and extension. Weights and inference code are…
- [Krea Realtime 14B](https://aivideoatlas.com/guides/krea-realtime-14b-krea/): Krea's realtime model, distilled from Wan 2.1 14B with Self-Forcing into an autoregressive generator. You can change prompts…
- [Kandinsky 6.0 Pro (5s, Diffusers)](https://aivideoatlas.com/guides/kandinsky-6-0-pro-5s-diffusers-kandinskylab/): Kandinsky Lab's 6.0 Pro text- and image-to-video model with audio generation, packaged for Diffusers under an MIT license. Lite and…
- [Prism: native 2K joint video-audio model](https://aivideoatlas.com/guides/prism-native-2k-joint-video-audio-model-francisring/): A research model from Fudan, Tencent Hunyuan and Zhejiang University that natively trains joint video and audio generation at 2K. Its…
- [Ovi 1.1 (audio-video generation)](https://aivideoatlas.com/guides/ovi-1-1-audio-video-generation-chetwinlow1/): Ovi generates video and audio together using twin cross-fused backbones (Character AI and Yale). Version 1.1 makes temporally consistent…
- [daVinci-MagiHuman (GAIR & Sand.ai)](https://aivideoatlas.com/guides/davinci-magihuman-gair-sand-ai-gair/): A 15B single-stream transformer that generates human-centric video and speech audio together in six languages. The authors report a…
- [HunyuanVideo-Avatar](https://aivideoatlas.com/guides/hunyuanvideo-avatar-tencent/): Tencent's audio-driven human animation model: give it an avatar image (any style or scale) and an audio track, and it produces dynamic…
- [SoulX-FlashHead 1.3B (real-time talking heads)](https://aivideoatlas.com/guides/soulx-flashhead-1-3b-real-time-talking-heads-soul-ailab/): A 1.3B streaming talking-head model. The Lite version reaches 96 FPS on one RTX 4090 (or three real-time streams), and the Pro version…
- [SCAIL-2 (controlled character animation)](https://aivideoatlas.com/guides/scail-2-controlled-character-animation-zai-org/): An open model from Zhipu (zai-org) that animates a reference character from a driving video end to end, without pose skeletons or masks…
- [LivePortrait (Kuaishou / Kling team)](https://aivideoatlas.com/guides/liveportrait-kuaishou-kling-team-klingteam/): Efficient portrait animation from the Kuaishou Kling team: drive a still portrait with a video, with stitching and retargeting controls…
- [Mochi 1 preview (Genmo)](https://aivideoatlas.com/guides/mochi-1-preview-genmo-genmo/): Genmo's open text-to-video model, released under a permissive license, with a focus on high-fidelity motion and prompt adherence. Weights…
- [AnimateDiff-Lightning (ByteDance)](https://aivideoatlas.com/guides/animatediff-lightning-bytedance-bytedance/): Distilled AnimateDiff checkpoints (1, 2, 4 and 8 steps) that generate video more than ten times faster than the original AnimateDiff. They…

## Weekly digest

- [Latest digest (JSON)](https://aivideoatlas.com/digest/latest.json): new models, price changes, new shots and prompts, stable keys
- [Latest digest (Markdown)](https://aivideoatlas.com/digest/latest.md)
- [Digest (HTML)](https://aivideoatlas.com/digest/)

## Prompting guides by model and mode
- [How to prompt Seedance](https://aivideoatlas.com/guides/seedance/) (checked 2026-10-11): [Text to video](https://aivideoatlas.com/guides/seedance/text-to-video/), [Image to video](https://aivideoatlas.com/guides/seedance/image-to-video/), [Start & end frame](https://aivideoatlas.com/guides/seedance/start-end-frame/), [Reference to video](https://aivideoatlas.com/guides/seedance/reference-to-video/), [Video to video](https://aivideoatlas.com/guides/seedance/video-to-video/), [Lip sync](https://aivideoatlas.com/guides/seedance/lip-sync/)
- [How to prompt Kling](https://aivideoatlas.com/guides/kling/) (checked 2026-10-11): [Text to video](https://aivideoatlas.com/guides/kling/text-to-video/), [Image to video](https://aivideoatlas.com/guides/kling/image-to-video/), [Start & end frame](https://aivideoatlas.com/guides/kling/start-end-frame/), [Reference to video](https://aivideoatlas.com/guides/kling/reference-to-video/), [Video to video](https://aivideoatlas.com/guides/kling/video-to-video/), [Lip sync](https://aivideoatlas.com/guides/kling/lip-sync/)
- [How to prompt Veo](https://aivideoatlas.com/guides/veo/) (checked 2026-10-11): [Text to video](https://aivideoatlas.com/guides/veo/text-to-video/), [Image to video](https://aivideoatlas.com/guides/veo/image-to-video/), [Start & end frame](https://aivideoatlas.com/guides/veo/start-end-frame/), [Reference to video](https://aivideoatlas.com/guides/veo/reference-to-video/), [Lip sync](https://aivideoatlas.com/guides/veo/lip-sync/)
- [How to prompt Runway](https://aivideoatlas.com/guides/runway/) (checked 2026-10-11): [Text to video](https://aivideoatlas.com/guides/runway/text-to-video/), [Image to video](https://aivideoatlas.com/guides/runway/image-to-video/), [Video to video](https://aivideoatlas.com/guides/runway/video-to-video/), [Lip sync](https://aivideoatlas.com/guides/runway/lip-sync/)
- [How to prompt Luma](https://aivideoatlas.com/guides/luma/) (checked 2026-10-11): [Text to video](https://aivideoatlas.com/guides/luma/text-to-video/), [Image to video](https://aivideoatlas.com/guides/luma/image-to-video/), [Start & end frame](https://aivideoatlas.com/guides/luma/start-end-frame/), [Video to video](https://aivideoatlas.com/guides/luma/video-to-video/)
- [How to prompt Hailuo (MiniMax)](https://aivideoatlas.com/guides/hailuo/) (checked 2026-10-11): [Text to video](https://aivideoatlas.com/guides/hailuo/text-to-video/), [Image to video](https://aivideoatlas.com/guides/hailuo/image-to-video/), [Start & end frame](https://aivideoatlas.com/guides/hailuo/start-end-frame/), [Reference to video](https://aivideoatlas.com/guides/hailuo/reference-to-video/), [Video to video](https://aivideoatlas.com/guides/hailuo/video-to-video/), [Lip sync](https://aivideoatlas.com/guides/hailuo/lip-sync/)
- [How to prompt LTX](https://aivideoatlas.com/guides/ltx/) (checked 2026-10-11): [Text to video](https://aivideoatlas.com/guides/ltx/text-to-video/), [Image to video](https://aivideoatlas.com/guides/ltx/image-to-video/), [Start & end frame](https://aivideoatlas.com/guides/ltx/start-end-frame/), [Video to video](https://aivideoatlas.com/guides/ltx/video-to-video/), [Lip sync](https://aivideoatlas.com/guides/ltx/lip-sync/)
- [How to prompt Wan](https://aivideoatlas.com/guides/wan/) (checked 2026-10-11): [Text to video](https://aivideoatlas.com/guides/wan/text-to-video/), [Image to video](https://aivideoatlas.com/guides/wan/image-to-video/), [Start & end frame](https://aivideoatlas.com/guides/wan/start-end-frame/), [Reference to video](https://aivideoatlas.com/guides/wan/reference-to-video/), [Video to video](https://aivideoatlas.com/guides/wan/video-to-video/), [Lip sync](https://aivideoatlas.com/guides/wan/lip-sync/)
- [How to prompt Grok Imagine](https://aivideoatlas.com/guides/grok-imagine/) (checked 2026-10-11): [Text to video](https://aivideoatlas.com/guides/grok-imagine/text-to-video/), [Image to video](https://aivideoatlas.com/guides/grok-imagine/image-to-video/), [Start & end frame](https://aivideoatlas.com/guides/grok-imagine/start-end-frame/), [Reference to video](https://aivideoatlas.com/guides/grok-imagine/reference-to-video/), [Video to video](https://aivideoatlas.com/guides/grok-imagine/video-to-video/), [Lip sync](https://aivideoatlas.com/guides/grok-imagine/lip-sync/)
- [How to prompt Higgsfield](https://aivideoatlas.com/guides/higgsfield/) (checked 2026-10-11): [Text to video](https://aivideoatlas.com/guides/higgsfield/text-to-video/), [Image to video](https://aivideoatlas.com/guides/higgsfield/image-to-video/), [Start & end frame](https://aivideoatlas.com/guides/higgsfield/start-end-frame/), [Reference to video](https://aivideoatlas.com/guides/higgsfield/reference-to-video/), [Video to video](https://aivideoatlas.com/guides/higgsfield/video-to-video/), [Lip sync](https://aivideoatlas.com/guides/higgsfield/lip-sync/)

## Blog
- [Blog index](https://aivideoatlas.com/blog/) · [RSS](https://aivideoatlas.com/blog/feed.xml)
- [What AI video costs per second (October 2026)](https://aivideoatlas.com/blog/ai-video-cost-per-second-october-2026/) (Atlas data, checked 2026-10-11): Every supported per-second price we track, the cheapest option for each generation mode, and what a 30-second video costs. Vendor-stated prices only, with check dates.
- [How to keep a character consistent across AI video shots](https://aivideoatlas.com/blog/consistent-character-ai-video/) (How-to, checked 2026-10-11): Use each model's reference mode, give every reference image one job, and lock the wording. Here is how it works on Seedance, Kling and Veo, with sources.