Anima FX

at the intersection of science and art.
Filmmaking / VFX / Generative AI / Music

[Kaku Drop 架空飴 @KakuDrop]

Seedance検証動画まとめ（2026.02–07）

ここ半年で制作した、プレビズをリファレンスとして使用した生成動画をまとめました

狙ったカメラワークや人物の細かな動きを高い再現性でコントロールでき、ランダム性が少ないため制作時間を見積もりやすく、後から細かな修正にも対応しやすいのが大きなメリット

ほとんどのAI案件でこの手法を使ってます

使用ツール
・Cinema 4D
・Unreal Engine
・After Effects

#UE5 #生成AI

[Jon Finger @mrjonfinger]

Best way to learn is to play.

[Larus Canus @MrLarus]

🤯 Depth videos perfectly solve false flags on reference videos — and can perfectly recreate both martial arts and dance!

Turned a Guan Dao martial arts clip into a Depth motion reference, swapped the fighter for a market auntie, and moved the scene to a T-junction inside a local market 🤣

🌟 Workflow:
1. Pick a reference clip under 15 seconds
2. Convert it to Depth with Depth Anything V2
3. Generate a new character + scene
4. Feed everything into Seedance with the prompt below

🌟 Depth video conversion:
You can build a local Depth converter with Codex — prompt in the comments.

This goes way beyond trending dances.
Martial arts, polearms, and other complex movements can all be transferred cleanly with Depth!

Workflow + Prompt below 👇

[Kiber Alla @Kiber_Alla]

I experimented a lot with the prompt until I landed on this version😎
Only face reference + exact 15-second audio. Generated in @higgsfield_ai Seedance 2.0.
Small tip: when uploading reference audio, cut it precisely to whole seconds (6, 8, 10, 15…) with no leftover tails 🎵

Prompt: A cinematic 15-second music video shot in a dark modern dance studio with smooth grey reflective floor, black walls and horizontal neon light tubes. Continuous dynamic camera movement, mostly medium shots and close-ups, never too wide. The woman is constantly moving, no freezes or static poses.
Main subject: young woman with messy medium-length wavy brown hair with bangs partially covering her face, freckles on nose and cheeks, blue-grey eyes, full glossy lips. She wears a tight black fishnet bodysuit. She is singing the entire time with clear, precise lip-sync, mouth actively moving, intense emotional expression.
Lyrics: "Ye! Ye! You keep a box of names / In the drawer by your bed / Polaroids and ticket stubs / Stuffed under the red / You never take one thing / You take the whole last spark / Leave a little thumbprint / On every private heart".
0-2s: Tight medium close-up. She leans her upper body back, head tilting, singing passionately with strong lip-sync, hair falling over her face, body arching, one hand sliding across her chest.
2-4s: Camera slowly pushes in and circles. She comes out of the deep arch, torso still bent forward, hands on her thighs, lifting her head and looking straight into camera while singing with aggressive lip-sync. Three male dancers of different appearances (different ethnicities, hair styles and builds) wearing black tank tops and black wide pants are already close around her, moving with her in low tense postures. The other two men are visible at the edges of the frame, approaching.
4-7s: Medium close-up. She drops lower, body still in constant motion, hair swinging, singing intensely with clear mouth movements, sharp head turns, eyes locked on camera. Male dancers stay close, their hands lightly touching her as they move together.
8-12s: Medium shot with slow camera drift. Exactly five male dancers of completely different appearances, all wearing black tank tops and black wide pants, surround her tightly on the floor in a dense, intertwined formation. She is in the center, body still moving, upper body rising and shifting, singing with strong lip-sync. All five men move subtly with her, never static. The men never fully obscure her body.
13-15s: Dynamic medium shot. The five diverse male dancers lift her into the air in a powerful deep backbend. Her body is fully extended and arched, head thrown back, still singing with clear lip-sync. While holding her they gently rock her up and down in time with the beat. The camera starts from a clear side view of her arched body and smoothly transitions to a frontal view of her face. At the end they lower her smoothly onto her feet; she lands and immediately continues singing as the five men stay low on the floor around her. The men never fully obscure her.
High fashion dance energy, sweaty skin, sharp timing, continuous fluid motion of the woman, priority on accurate lip-sync in every frame.
Rules: no hand morphing, no body distortions, clean stable anatomy, fingers and hands remain consistent and natural throughout the entire video.

#AIvideo #AIMusicVideo #AIFilmmaking

[MIKE @mikenevermiss]

THIS DEVELOPER JUST KILLED THE VOICE CLONING INDUSTRY WITH ONE GITHUB REPO.

Claude can now speak in your own voice across 23 languages through a single MCP call.

Free. Local. Offline.

What used to cost $22 to $330/month with ElevenLabs is now open source under the MIT license.

Jamie Pine just dropped voicebox on GitHub, and it already has over 41k stars.

It clones any voice from just 10 seconds of audio, lets you choose from seven different TTS engines, and runs entirely on your own machine, so your voice and recordings never leave your computer.

Connect it to Claude Code, Cursor, Cline, or any MCP compatible agent with a single voicebox.speak call, and your AI can start replying in your cloned voice.

It also adds global voice dictation that works in any app with one hotkey and can generate speech in 23 languages, including Arabic, Japanese, and Polish.

One open source app now replaces both ElevenLabs and Wispr Flow.

If you’ve been waiting to give your AI agent a voice, this is it.

Repo below 👇

[WasifAI @doctorwasif]

Made with Seednace 2

Prompt:
CAMERA:
DV 16mm tape camcorder handheld footage feel. Point of view of CHASE holding the camera directly in hand. Maintain hand shake, misaligned framing, delayed focus pull, clumsy zoom in/out, occasional self-cam framing where the face gets cut off, and imperfect shots that lose the subject. Every shot is CHASE holding the camcorder herself, filming in selfie-cam or first-person style. The camcorder itself never appears on screen.
LOOK:
DV 16mm tape camcorder footage look. Soft, slightly blurry digital tape quality, faint tape noise, highlights that bloom slightly in low light, auto-exposure that flickers subtly, muted color contrast, realistic skin tones.
STYLE:
Late-night, low-energy-but-happy vibe — tired but satisfied after a long practice session. Handheld throughout, quieter and slower than a bubbly daytime vlog, occasional heavy breathing between lines, genuine unposed exhaustion mixed with pride.
Character
CHASE — a Korean idol in her 20s. Long straight black hair tied up or slightly messy from practice, elegant yet lovely Korean features, glowing skin with a light sheen of sweat, big eyes. Slim build. Wearing a modest long-sleeve athletic top and loose-fit joggers or sweatpants, fully covered arms and torso, sneakers. No jewelry.
Setting
An empty dance practice studio late at night — mirror walls lining one side, wooden floor, a speaker in the corner, a water bottle and towel by the wall, dim overhead lighting with the hallway lights off outside the studio windows.
Storyboard
(~2s, propped camera against the mirror, medium shot) She walks into frame, breathing a little heavy, wipes her forehead with the back of her hand, small tired smile. CHASE: "Okay... just finished practice, it's so late."
(~2s, handheld, slow pan across the room) Camera drifts across the empty mirror wall and the quiet studio, then back to her. CHASE (off-screen, softly): "Whole place is empty now, just me."
(~2s, medium handheld, by the wall) She grabs her water bottle, takes a long sip, exhales in relief afterward. CHASE: "Needed that so bad."
(~1.5s, macro insert, shallow DOF) Close-up on her hand wiping condensation off the water bottle, a drop of sweat catching the light. No dialogue — soft breathing sound only.
(~2s, medium handheld, facing the mirror) She sets the camera down propped against the wall, steps back, and does a few quick, sharp dance moves — a short combo tease — then laughs at herself afterward.
(~2s, handheld, close on her face) She fans herself with her hand, cheeks flushed, hair slightly damp, grinning at the lens. CHASE: "Okay that took more out of me than I thought."
(~1.5s, quick punch-in, tight selfie) She leans in close, still catching her breath, eyes bright despite the tiredness. CHASE (softly): "But it felt good though."
(~2s, arm's-length selfie finish) She grabs her towel, drapes it over her shoulder, gives the lens a small tired wave and a genuine smile before reaching to end the recording. CHASE (quietly): "Okay, going home. Night guys."

[OAK @_OAK200]

Exploring a new storyboard format: Depth Map Storyboards.

Instead of letting Seedance 2.0 inherit the storyboard's visual style, I used a reference image to define the tone and look, while the depth-map storyboard defines the composition and camera framing.

workflow + system prompt below 🧵

[Purz.ai @PurzBeats]

1. Reference Video -> Convert to Depth Map
2. Depth Map -> Seedance 2.0 (Reference Video)
3. Add Reference Image
4. Set Duration / Resolution / Aspect
5. Pass Audio from Reference Video -> Final
6. Hit Run

[LTX.io @ltx_io]

No reshoot required.

Our new Clean Plate IC-LoRA for LTX-2.3 removes people, pedestrians, and vehicles from a clip and rebuilds the empty background behind them.

🎬 Full-frame subject removal, no mask required
🏗️ Keeps architecture, ground markings & foliage intact
⚙️ Runs as a video-to-video LoRA on @ComfyUI

[Sagi Polaczek 🦜 @PolaczekSagi]

🎬🎨 LTX-2.3-Sync-LoRA, dataset and weights are out!

check it out yourself :)
https://t.co/ZBvfwF2iPt

[Reid Hannaford @reidhannaford]

Ok, this is absurd.

You can choreograph a complex action scene in Blender with basic shapes, then let Seedance make it real.

You need to try this AI filmmaking workflow:

1. Generate a start frame in Midjourney

2. Block out the action in Blender

3. Feed both to Seedance

My Blender reference was just rough timing, camera shake, and spatial choreography, and Seedance tracked the speed, motion, and action way better than I expected.

This is the difference between describing a shot and directing one.

[Stable Diffusion Tutorials @SD_Tutorial]

After 🙂📹Cameraman Lora V1 now V2 released

LTX-Video 2.3 IC-LoRA: Cameraman v2

A fine-tuned In-Context LoRA (IC-LoRA) adapter for LTX-Video 2.3 (22B), trained to replicate camera movements from a reference video.

👇Hf repo:
https://t.co/n5R0Ui2bz8

[Lovis Odin @OdinLovis]

Its coming tomorrow and no, its not seedance :), it should follow and respect much more the 3d input render, and its gonna be open source !

[Reid Hannaford @reidhannaford]

This is getting ridiculous.

You need to try this AI filmmaking workflow.

My Blender reference is embarrassingly simple. You can drive a precise multi-character shot with nothing but basic shapes.

1. Generate a start frame in Midjourney

2. Block out the scene in Blender with boxes, animate the camera

3. Feed both to Seedance

This feels like a real unlock. Your 3D reference doesn't need to look good.

[ComfyUI @ComfyUI]

One animation. Different visual styles.

This workflow uses Seedance 2.0 in ComfyUI with reference images to explore different looks while preserving the same motion and camera movement. In this example, the animation starts with a simple Blender scene, making it easy to compare different creative directions.

Featured clips courtesy of @AIWarper, @reidhannaford, and @jmsvid.

To try this workflow, link below 👇

[LTX @ltx_model]

(1/5) Open weights. A full trainer. 22B parameters you can fine-tune yourself.

LTX doesn't just generate video, it lets you build custom LoRAs that shape style, motion, and quality across every generation. Our community is already on it.

Here are 3 LoRAs worth watching 🧵

[Brie Wensleydale🧀🐭 @SlipperyGem]

Tori29umai-san's amazing Qwen Edit lora collection page. Some very neat re-posing, erasure, abstraction and other utility loras.

Also some links to other unique utility and niche QE2511 lora.

Always love tori-san's amazing work.
https://t.co/NIRB3sDOIO

[Wildminder @wildmindai]

Aurora- gent-driven video editor designed to fix lazy user requests.
A bridge between a vague idea and a high-quality video.

- Qwen3-VL-8B + Wan2.2
- automatically retrieves assets, makes masks
- handles object insertion, removal, bg changes in one pipeline

useful for brand placement, concept editing, smart swaps etc

https://t.co/sgpPX2R4A2

[Kirill @kirillk_web3]

Anthropic CEO after realizing the founder of a $20B Chinese AI company dropped a free 40-minute masterclass

[Jordan Daniel Chesney @jordandchesney]

You know that super annoying overlay texture pattern you get on AI images, particularly with Nano Banana Pro and GPT 2.0?

Here's how to get rid of it.

Toss your image into @magnific as a reference, select the Nano Banana Pro model, and prompt:

Recreate this image exactly, detail for detail and restore fidelity, making it high resolution, and crisp, and clear. Exactly maintain the original colors.

Credit to @DavidLaChanceJr for figuring this out.

Hope this helps.