BUKU

AI Video and Film Tools & Prompts • AI News, Video/Image Generative Ai, AI Agents and discussing the future of Ai creative workflows @Superba_ai

[Curious Refuge @CuriousRefuge]

We just tested what might be the most accurate motion transfer workflow we've seen so far. It's a little more involved than a standard workflow, but the results are pretty impressive.

Here's the basic workflow:

1. Start with your reference footage. Create character and environment references.

2. Convert the reference footage into a depth map (with Depth-Anything tool on Fal: https://t.co/cYrMeukGtu).

3. (Optional) Layer on additional guidance like colorized character masks (with Meta's Segment Anything: https://t.co/4p3Gg3bZeu), and or skeleton poses (with https://t.co/kjFlboPSAC).

4. Feed the depth map into Seedance 2.0 Omni as your motion reference along with your character and environment references.

5. Generate your final video.

After testing several variations, the depth map workflow consistently produced the cleanest and most accurate motion transfer. If you're trying to recreate specific performances or complex movement, this is one of the closest AI workflows we've seen to achieving production-quality results.

[Luma @LumaLabsAI]

No matter how you call it, football, soccer, fútbol, it's the same ball, the same grass, and the same passion that pulls the whole world in. Made with Luma.

[el.cine @EHuanglu]

omg.. AI just fixed b&w silent films

this AI video composer can analyse the story and generate SFX and music for entire film.. and chat with agent to add and edit

check out workflow:

[HeyGen @HeyGen]

We gave HyperFrames a media library

10k+ tracks, 75k+ images, sfx, logos
free with a HeyGen login

Plus access to our generative models

Assets save to your machine, so the next project skips the search

/media-use ↓

[Higgsfield AI 🧩 @higgsfield]

Free Mode is live in Higgsfield Supercomputer.

The LLM inside is now free to use for brainstorming, prompt writing, scripting, research, and project planning. Credits kick in only when you generate.

A Supercomputer-level LLM, yours to use.

[A.I.Warper @AIWarper]

OmniVoice Zeroshot Clone + VEED Fabric Test

VEED Fabric accepts audio + image and creates a lipsync video.

Obviously.... turn your volume up.

[Zeto @ZetoGroovin]

【精度高いAIダンス動画の作り方】
ダンスモーションを深度マップに変換してSeedance2.0でキャラとモーション動画を参照させてダンス動画作ってみた！
引用元1p ( @impalementd )さんの作り方を参考にさせていただきました！
深度マップにするとモデルに渡す情報が「動き」だけになるからなのか、ダンスの精度が高くなってる気がします。

そして、KnRoco ( @roco_kn_roco )さん、おじさんダンスのアイデアありがとうございました☺️

[Martin LeBlanc @martinleblanc]

Prompting for Seedance 2.0 tip 🫆

It doesn't have to be complex to give good results.

You can get surprisingly far with a good reference image + a simple narrative prompt. In this video, i combined 2 Seedance 2.0 generations (prompts below):

Part 1:

"an animator is struggling to come up with ideas. it's driving him made. he throws out the drawing. tries again. pulls his beard. starts over. paper thrown into trash can.

comedy. animation style. multi-scene. high end animation."

Part 2 (giving it part 1 video as reference)

"continue this video.

after struggling to come up with a concept for a character, the artist take a deep breath and say to him self to focus harold.

then he draws a beautiful and cool badass princess with a gun. he holds it up proud and whispers that's it.

comedy. animation style. multi-scene. high end animation."

[BUKU @buku_ai]

@maxxmalist Agent

[MAX @maxxmalist]

Fable 5 is INSANE for creating ads

i built an agent that studies your competition and thousands of viral ads, then gives you a full viral blueprint for your brand to copy

just feed it a product photo and a landing page link and competitors names, 3 minutes later you've got a proven creative playbook for your ads, here's how it works:

- scans your brand's own website (copy, offers, structure, CTAs)
- scans competitor websites (you list them, or Claude finds likely ones for you)
- pulls live ad data straight from Meta Ad Library + TikTok via spytools
- extracts proven hooks, scripts, and visual/creative patterns from every source
- synthesizes everything into one swipe-file library
- output is a ready-to-paste doc, drop it into Claude and generate new ad scripts from proven angles instantly
- runs locally, one command, your own API keys, no video generation step slowing you down

runs 100% local, without $300/mo on spytool subscriptions or agency fees, full control, and API cost only

RT + reply w/ "AGENT" and i'll send it to you so you can use it for your brand (must follow so i can DM)

[TechHalla @techhalla]

Two cinematic prompts for Seedance 2.0 right here 👇

[STYLE + CAMERA + ATMOSPHERE]
Ultra-photorealistic cinematic 15-second action sequence from a grounded action thriller film. Nighttime at an abandoned industrial train yard. Old trains, rusted tracks, broken platforms and warehouses. Strong moonlight and industrial lighting. The visual language is gritty and realistic with hyper-realistic practical destruction. Camera is handheld-dynamic with urgent moves.

[IMAGE REFERENCES]
No reference images provided. Generate a fully consistent lead character: a male fugitive in his mid-30s, short hair, intense expression. He wears a dark jacket, jeans and boots. Maintain exact same appearance and clothing throughout the clip.

[TIMELINE SECOND BY SECOND]
0-3s: [Dynamic handheld tracking shot from side-rear] The man runs across the train yard as a freight train derails violently after hitting a collapsed section of track. Massive train cars tip over and crash into the ground, sending metal, wood and cargo flying. The camera tracks him urgently as the destruction spreads.

3-7s: [Slow continuous orbiting camera moving around the frozen destruction] At the peak of the derailment, everything freezes in perfect realistic physics. Huge train cars, twisted metal, wooden debris and clouds of dust hang motionless in the air with accurate weight and trajectories. The camera performs a smooth, continuous orbit through the frozen chaos, moving between large suspended train cars and passing close to sharp metal fragments while the man remains visible.

7-15s: [Dynamic tracking shot as time resumes] At the 7-second mark time snaps back to forward motion with a slight realistic temporal residue. Some outer debris shows a very subtle reverse lag before continuing. The man has used the frozen moment to dive behind a concrete barrier. When motion resumes, several large pieces of metal miss him. He stays low and runs toward an open warehouse as debris finally crashes down. The camera tracks with him through the dust.

[STYLE & QUALITY BOOSTERS]
Photorealistic 8K, hyper-realistic rigid body destruction with correct material properties (metal, wood, train parts), perfect frozen mid-air physics, seamless transition from freeze to resume, natural dust interaction, heavy cinematic motion blur on fast debris, stable character performance, movie-level practical destruction VFX quality.

[TopviewAI @TopviewAIhq]

Prompts aren’t enough when your shot needs precision.

With Topview 3D Shot Composer, you can visually stage characters, props, and camera framing before generating your video.

Less guessing. Fewer rerolls. More predictable shots. 🎬

Stop describing your shots. Start directing them.

#TopviewAI #AIVideo #AIFilmmaking #AIStorytelling #3DShotComposer

[rob - comfyui @hellorob]

Claude Fable running ComfyUI workflows through the Comfy MCP is a cheat code.

→ Claude pulled the shot from the web, auto-detected the scene cuts + trimmed it
→ ran my saved depthanything v3 + openpose workflow to build the driving reference video
→ scrubbed every frame for the sharpest one, then character swapped me in with gpt-image-2 exactly how I directed it: wearing a tuxedo, liminal space environment, no background characters
→ wrote the seedance 2.0 prompts + ran the gens
→ stitched together the 3-panel comparison you're watching

The preprocessing + prompt writing is usually most of the work on a clip like this. With the MCP I didn't touch any of it. Didn't need to look at a single node lol.

[VoxelPlot @voxelplot]

Seedance 2.0 - Advanced Workflows Series

12. Cinematics with Unreal Engine and Claude Fable 5
Fable 5 is an absolute beast model that can take control of Unreal Engine and create videogames.

We can build scenes as a little video game with physics and assets and configure a playable character to create a cinematic scene.

In this example I created a scene of an astronaut lost in space floating between asteroids.

I created a zero gravity environment and made assets like cubes and spheres representing asteroids interact in this environment.

I recorded the gameplay and later place a camera to build the cinematic.

Workflow + Prompts 👇

[el.cine @EHuanglu]

AI imagine Paris in 1920s

[LudovicCreator @LudovicCreator]

🎨 SEEDANCE 2 🎨

Prompt :

Immersive first-person flying camera perspective, no visible drone or flying device. The camera dives through an ancient jungle temple swallowed by storm clouds, racing between vines, stone statues, waterfalls, and glowing ruins. At the end, the temple opens into a massive underground sun, releasing golden shockwaves and levitating stone rings. Continuous POV shot, no cuts, aggressive banking, cinematic motion blur, volumetric mist, high-end fantasy VFX.

Made in @dreamina_ai

#DreaminaCPP #DreaminaAI

[Theoretically Media @TheoMediaAI]

Crazy impressive results using Claude Fable to build out a pose/depth previs for Seedance.

This was inspired by Josh Daws' build-- but of course I made a few tweaks I'll showcase on the channel later this week.
Another example below that shows why I think this is awesome:

[Higgsfield AI 🧩 @higgsfield]

Introducing Shorts Studio, powered by Gemini Omni Flash.

Adapt any clip to the formats people watch, with pacing and editing built to grab attention from the first second.

This is how short-form video goes viral now.

Available on Higgsfield · MCP · Supercomputer

[Higgsfield AI 🧩 @higgsfield_ai]

No previous AI model could generate VFX this good.

[Salma @Salmaaboukarr]

quick test
mj v8.2 models x seedance 2