# anymove Adopt this skill: https://proskills.md/skills/other/patch-gg-anymove-skills-anymove Page: https://proskills.md/skills/other/patch-gg-anymove-skills-anymove This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required. ## File: skills/anymove/SKILL.md size: 6052 sha: 6954e2413a5185b85b864ee48ed1ab3fcd0b3e70 upstream: https://github.com/patch-gg/anymove/blob/main/skills/anymove/SKILL.md ````text --- name: anymove description: Motion capture for any creature from one AI video, with the anymove repo. A video model films a rigged 3D creature from two cameras in one frame, a DINOv2 joint reader trained on that creature finds every joint in both views, and the rig is fitted to them and exported as a GLB. Use when someone wants to animate a non-human creature (dragon, spider, wolf, monster) from a text prompt or an AI video, asks how anymove works, or needs to know which step comes next; it routes to anymove-rig, anymove-film, anymove-reader, anymove-capture, anymove-pack and anymove-lora. license: Apache-2.0 compatibility: Needs an NVIDIA GPU with CUDA (12 GB to train a reader, 24 GB is safer), Blender 5.x, Python 3.11, and a fal.ai key for video generation. Runs on Linux and on Windows in Git Bash. --- # anymove Animate any rigged creature from one AI video. The trick is the frame: one image holds two orthographic views of the creature at the same scale, front on the left and side on the right, sharing the vertical axis. A joint sits on the same pixel row in both halves, so the front view gives left-right and height, the side view gives front-back and height, and together they pin the joint in 3D. The method is @CanItCode's; the LoRA step is @Graalitoo's idea. ## The pipeline | step | once per | what happens | skill | |---|---|---|---| | 1. mesh | creature | a textured 3D model (Tripo H3.1 from one image, or your own GLB), facing -Y, real size | anymove-rig | | 2. skeleton | creature | joints placed in `assets//rig.json`, rig built and skinned in Blender | anymove-rig | | 3. limb colours | creature | each limb painted its own colour so left and right never swap | anymove-rig | | 4. two cameras | move | the painted reference frame plus a strict prompt go to MiniMax H3 Max on fal | anymove-film | | 5. teach a reader | creature | 2,200 random poses rendered with known joints; DINOv2 learns this creature | anymove-reader | | 6. read every joint | clip | the reader finds every joint in both views, every frame | anymove-capture | | 7. two views, 3D | clip | shared heights tie the views; the pair gives each joint in 3D | anymove-capture | | 8. the rig follows | clip | forward kinematics in torch fitted to both views; GLB out | anymove-capture | | 9. the pack | creature | score the takes, keep the best, cut loops and root motion; one GLB with every move | anymove-pack | | optional | creature | a MiniMax H3 LoRA that keeps the two-camera layout and colours more reliably | anymove-lora | ## Before anything 0. **Check it's the right tool.** If the person only wants a creature, look in Patch's Assets first: nine are ready. anymove suits big single gestures, and doesn't do eight-legged walking, lying down, bird wings or tail swipes (see the README). Check there's an NVIDIA card before anything else; without one, stop and say so. 1. Work in an anymove checkout. If the working directory has no `tools/capture.sh`, clone it: `git clone https://github.com/Patch-gg/anymove && cd anymove`. 2. Set up once: `python3.11 -m venv .venv`, then `.venv/bin/pip install torch==2.11.0 --index-url https://download.pytorch.org/whl/cu128` and `.venv/bin/pip install -r requirements.txt`. Blender 5.x must be on PATH, or set `BLENDER=/path/to/blender`. **On Windows,** run everything in Git Bash, use `py -3.11 -m venv .venv` and `.venv/Scripts/` where these say `.venv/bin/`, and set `BLENDER`. `tools/*.sh` handle the rest. If you call Blender yourself rather than through them, give it absolute paths: on Windows it reads a relative output path from the drive root. 3. For video generation and LoRA training, put `FAL_KEY=...` in `.env` (git ignores it) or export it. Never print it. 4. Every command takes a creature name; its config is `assets//creature.json` and every output lands in `runs//` (reference frame, dataset, `reader.pt`, videos, clips). The scripts set `MOCAP_CREATURE` for you; when you run a `python -m mocap...` module by hand, set `MOCAP_CREATURE=assets/` first, or the wolf's layout applies. ## Which step next - No `assets//model.glb`: make or fetch the mesh. Examples: `tools/fetch_examples.sh ` (wolf, dragon, spider, demon). New creature: anymove-rig. - No `assets//rigged/rigged.blend` or `runs//ref/ref.png`: `tools/prep.sh ` then `tools/rig.sh ` (anymove-rig). - No `runs//reader.pt`: anymove-reader (about 45 min on one RTX 4090), or `tools/fetch_examples.sh --readers`. - No clip for the move: anymove-film (about $0.26 a 5 s clip, and about 7 clips for a usable move). - A clip: anymove-capture, `tools/capture.sh `. - Several good takes: anymove-pack, `tools/pack.sh `. - Clips keep swapping limb colours or the halves drift apart: anymove-lora. ## Try it without a GPU The repo carries the dragon's roar as read by its reader. Fit it on the CPU in about a minute and a half: ```bash mkdir -p runs/dragon/clips/roar MOCAP_CREATURE=assets/dragon .venv/bin/python -m mocap.solve examples/dragon_roar/det.npz \ assets/dragon/rigged/rig_info.json runs/dragon/clips/roar/motion.json ``` It prints the paw agreement (about 0.93) and the reprojection error per view; `motion.json` holds the keyframes. ## Costs and time (October 2026, one RTX 4090) **Quote the all-in numbers, not the price of one clip:** about $3 for a usable move, and about $17 and a couple of hours for a new creature with about 5 moves (about $11 of AI services on the person's own card). A move took about 7 clips on average ($1.80), and 58% of captured clips passed the checks. - Tripo H3.1 mesh with HD texture: $0.40. MiniMax H3 Max clip: about $0.26 for 5 s (H3: $0.30). - Dataset and reader training: about 75 min on one RTX 4090. Reading a clip: about 12 s. Fitting: about 45 s. GLB and renders: about 3 min. - A LoRA: $0.01 a training step, so 1,200 steps cost about $12 and take about 2 h on fal. Say what a step will cost before calling fal, and confirm with the person before spending on a batch. ```` ## File: README.md upstream: https://github.com/patch-gg/anymove/blob/main/README.md ````text patch. anymove. motion capture for any creature, from one AI video.

Six panels: a dragon, a giant spider, a fire demon and a wolf, all moving; then an AI video shows the dragon from the front and the side at once; every joint is found in both views; the two views stand up as walls and pin each joint in 3D; the rig lands on the points; a fire demon, a spider and a wolf move the same way. **@patch_gg** · dragon, giant spider, fire demon, wolf · about $3 for a usable move, all in. anymove turns one AI video into an animation for any rigged creature, wings, tails and eight legs included. A video model films the creature from two cameras in one frame, front on the left and side on the right. A joint reader trained on that one creature finds every joint in both views. A joint sits at the same height in both, so the pair pins it in 3D, and the rig is fitted to those joints frame by frame and exported as a GLB. The method is [@CanItCode](https://www.youtube.com/watch?v=AS92HYsEBqo)'s; the MiniMax H3 LoRA step is [@Graalitoo](https://x.com/Graalitoo/status/2112548557576380659)'s idea. This repo is our working version of both, with the agent skills to run it. **Just want the creatures?** [Nine are ready in Patch's Assets](https://staging.patch.gg/create/toolbox/assets?source=anymove), with 4 to 7 moves each: T-rex, knight, horse, centaur, woman, ogre, ape, mech and scorpion. ## before you start. - **You need:** an NVIDIA card (12 GB to train a reader, 24 GB is safer), Blender 5.x, Python 3.11 and a [fal](https://fal.ai) key. Without the card it doesn't run, and there's no cloud version. - **It costs about $3 for a usable move, all in,** and about $17 and a couple of hours for a new creature with about 5 moves. [The numbers are below](#what-it-costs). - **Most clips don't make it.** A move took about 7 clips on average, and 58% of captured clips passed the checks. ## what it's good at, and what it isn't. **Good at:** big single gestures on any body plan: roars, slams, rearing up, chest beats, stomps, taking off. Walks and runs work on two and four legs. You get a real animation on a real skeleton, in a file any engine plays. **Not good at:** - **Eight-legged walking.** The two views disagree about which legs are up (0.36-0.49). Scorpions and spiders can rear, bite and strike, but they don't walk. - **Lying down.** The reader learns from random poses inside the joint limits, which don't include lying on a side. - **Bird wings.** The eagle's wings don't fit (15-30 px off), and it was left out of the nine. Bat-like wings do fit, on the dragon and the demon. - **Tail swipes.** The two views disagree about where the tail tip is. The T-rex's was dropped after six tries. - **Fine foot contact.** Feet slide 1 to 2 cm a step and nothing pins them yet. That's fine for most uses, and visible up close. - **Fast runs.** Runs look like fast walks in places: the video model doesn't lower the body on a run. - **Moving an animation to another creature.** An animation only fits the creature it was made for, and a new model needs a new reader. - **Light files.** Generated creatures are 55,000 to 60,000 triangles with 4K textures, which is heavy for a browser game, and there are no lighter versions yet. ## how it works. | | | |---|---| | A concept picture of a dragon, an arrow, and the textured 3D model it became. | **1 · a 3d model.**
One picture becomes a textured mesh at real size.
flux 3 picture, tripo h3.1 mesh · $0.40 | | The dragon as a faint x-ray with its white skeleton inside. | **2 · a skeleton.**
Bones placed on grid views, skinned in Blender.
42 bones: legs, wings, tail | | The dragon with each leg and wing painted its own colour, the right wing labelled. | **3 · limb colours.**
Every limb its own colour, so left and right never swap.
6 limbs, 6 colours | | The dragon from above, one camera at its face and one at its right flank. | **4 · two cameras.**
One camera at the front, one at the side, both views in one frame; a video model animates both at once from a prompt.
minimax h3 max on fal · 5 s, $0.26 | | A random training pose of the dragon in both views with its true joints drawn on. | **5 · teach a reader.**
A vision model learns this one dragon from random poses whose joints are known; its average miss falls from 40 px to 6 px.
dinov2 · 2,200 poses · 20 min on one gpu | | The AI clip with a white skeleton drawn over the dragon in both views. | **6 · read every joint.**
The reader finds every joint in both views, in every frame.
50 joints · 10 s a clip | | The two views stood up as walls at a right angle, the nose ringed on both, and the two lines meeting at the nose in 3D. | **7 · two views, 3d.**
Stand the two views up as walls at a right angle: each joint is where its two lines meet. The front gives side to side, the side gives nose to tail.
x from the front, y from the side, z from both | | The rig as an x-ray, its bones landed on the 3D points, stray points in grey. | **8 · the rig follows.**
The rig bends its bones onto the points, ignores the strays, and exports for any engine.
glb, 24 fps, no hand edits · under a minute a clip | Then the best takes become one file, with seamless loops and root motion ([docs/PACKS.md](docs/PACKS.md)). [docs/PIPELINE.md](docs/PIPELINE.md) has the file-by-file version. ## quick start. You need an NVIDIA GPU with CUDA (12 GB to train a reader, 24 GB is safer; reading and fitting need much less), Python 3.11, [Blender](https://www.blender.org) 5.x on your `PATH` (or `BLENDER=/path/to/blender`), and a [fal](https://fal.ai) key to make new clips. ```bash git clone https://github.com/Patch-gg/anymove && cd anymove python3.11 -m venv .venv .venv/bin/pip install torch==2.11.0 --index-url https://download.pytorch.org/whl/cu128 .venv/bin/pip install -r requirements.txt cp .env.example .env # then add your FAL_KEY; git ignores .env ``` **On Windows,** use [Git Bash](https://git-scm.com/downloads/win), and the same commands with the venv's other folder. Every `tools/*.sh` finds the venv and handles Blender's paths and Python's line endings. Blender usually isn't on your `PATH`, so point at it: ```b ````