camera-control
/camera-control
Animate a still with an explicit, repeatable camera move (named trajectories such as orbit, dolly or crane, or drawn ATI point tracks) using open-weights Wan Fun Camera and Wan ATI in ComfyUI. Use when the camera path must be exact rather than prompted.
- Author
- mojomast ↗
- Repository
- open-higgsfield-skills ↗
- Licence
- MIT
- Last repository change
- 30.10.2026
Assessment and security
- Files in this package
- 55
- Scripts
- 30
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 30.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 30 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: assets/motionfield_nodes/__init__.py, assets/motionfield_nodes/core/__init__.py, assets/motionfield_nodes/core/box.py, assets/motionfield_nodes/core/camera_da3.py, assets/motionfield_nodes/core/camera_embed.py, assets/motionfield_nodes/core/camera_lens.py, assets/motionfield_nodes/core/camera_post.py, assets/motionfield_nodes/core/camera_rig.py, assets/motionfield_nodes/core/camera_splat.py, asset
What it does and when to use it
Animate a still with an explicit, repeatable camera move (named trajectories such as orbit, dolly or crane, or drawn ATI point tracks) using open-weights Wan Fun Camera and Wan ATI in ComfyUI. Use when the camera path must be exact rather than prompted.
Original author description
Animate a still with an explicit, repeatable camera move (named trajectories such as orbit, dolly or crane, or drawn ATI point tracks) using open-weights Wan Fun Camera and Wan ATI in ComfyUI. Use when the camera path must be exact rather than prompted.
How it works
- Picture to 3D to camera move (agentY design)
SKILL.md preview
---
name: camera-control
description: Animate a still with an explicit, repeatable camera move (named trajectories such as orbit, dolly or crane, or drawn ATI point tracks) using open-weights Wan Fun Camera and Wan ATI in ComfyUI. Use when the camera path must be exact rather than prompted.
---
# camera-control
Run with `python scripts/comfy_client.py --url $COMFY_URL run workflows/<file> --set NODE.INPUT=VALUE --out out/`, and upload inputs first with `comfy_client.py upload <file>`. Before the first run, check the server with `python scripts/preflight.py --url $COMFY_URL workflows/<file>`. Node packs, model files, VRAM and weight licenses are in `references/requirements.md`. Use open-weights models only. LTX weights are under the Lightricks LTX-2 license, which is **not** an OSI-approved open-source license.
| graph | format | control |
|---|---|---|
| `wan_fun_camera_i2v.api.json` | API (motionfield) | `OF_Trajectory.trajectory` is a named move (default `locked-off`), plus strength, fps and seed. It goes to `OF_CameraEmbed` and then `WanCameraImageToVideo` |
| `wan_fun_camera_director.api.json` | API (motionfield) | the same chain without CLIP-vision, for a lighter graph |
| `ui/wan22_14b_fun_camera.ui.json` | UI (Comfy-Org) | Wan 2.2 14B Fun Camera with core camera-embedding nodes |
| `ui/wan21_fun_camera_1_3b.ui.json` | UI | 1.3B, so the smallest VRAM (draft tier) |
| `ui/wan_ati_trajectory.ui.json` | UI | ATI: draw point trajectories in the spline editor, so objects follow paths |
The motionfield graphs (MIT) use `{{PLACEHOLDER}}` strings. **Every** placeholder must be replaced with `--set` before you submit (`grep -o '{{[A-Z_]*}}' workflows/<file>` lists them). Pass numbers as JSON (`--set 9.width=832`). Their `OF_*` nodes are bundled in `assets/motionfield_nodes` (MIT; `dwpose_onnx` is Apache-2.0), and they need numpy, torch, opencv and onnxruntime on the **server**. Copy the folder to `ComfyUI/custom_nodes/`.
The valid trajectory names are the keys of the catalog in `assets/motionfield_nodes/core/camera_trajectory.py`. Read them there rather than guessing.
`workflows/ui/*.ui.json` are official Comfy-Org templates (MIT) in **UI format**, and most contain subgraphs. `comfy_client.py` refuses UI format. To use one: open it in ComfyUI, install the missing nodes and models that ComfyUI lists (they are also in `requirements.md`), then use **Workflow → Export (API)** to save it as `workflows/<name>.api.json`. Run `preflight.py` on the export and read off the node ids for `--set`. Node ids change when you export, so do not reuse ids from another graph.
## Picture to 3D to camera move (agentY design)
`references/agentY-camera-move-control.md` (MIT) describes the chain: picture → depth mesh → keyed camera move → rendered clip → control video for Wan Fun Control or an LTX IC-LoRA. In this collection that chain is `image-to-3d` or `previs-control-passes`, then `control-to-video`. The agentY tool names in that file do not exist here.
- Keep a move within about the depth of the picture. Moving further past the content shows holes.
- Check a camera claim with numbers (`shot-qc` motion and freeze), not with a VLM description.
Files in this package (55)
- SKILL.md 3 KB
- assets/motionfield_nodes/LICENSE 1 KB
- assets/motionfield_nodes/NOTICE 1 KB
- assets/motionfield_nodes/README.md 2 KB
- assets/motionfield_nodes/__init__.py 1 KB
- assets/motionfield_nodes/icon.png 2 KB
- assets/motionfield_nodes/moss_cuda_runner.py 1 KB
- assets/motionfield_nodes/nodes_audio.py 18 KB
- assets/motionfield_nodes/nodes_box.py 3 KB
- assets/motionfield_nodes/nodes_camera.py 20 KB
- assets/motionfield_nodes/nodes_director.py 4 KB
- assets/motionfield_nodes/nodes_mask.py 17 KB
- assets/motionfield_nodes/nodes_pose.py 8 KB
- assets/motionfield_nodes/nodes_provenance.py 3 KB
- assets/motionfield_nodes/nodes_relight.py 3 KB
- assets/motionfield_nodes/pyproject.toml 1 KB
- assets/motionfield_nodes/core/__init__.py 1 KB
- assets/motionfield_nodes/core/box.py 3 KB
- assets/motionfield_nodes/core/camera_da3.py 16 KB
- assets/motionfield_nodes/core/camera_embed.py 2 KB
- assets/motionfield_nodes/core/camera_lens.py 2 KB
- assets/motionfield_nodes/core/camera_post.py 3 KB
- assets/motionfield_nodes/core/camera_rig.py 26 KB
- assets/motionfield_nodes/core/camera_splat.py 3 KB
- assets/motionfield_nodes/core/camera_trajectory.py 22 KB
- assets/motionfield_nodes/core/director_rig.py 10 KB
- assets/motionfield_nodes/core/face.py 3 KB
- assets/motionfield_nodes/core/mouth.py 2 KB
- assets/motionfield_nodes/core/pose_draw.py 5 KB
- assets/motionfield_nodes/core/relight.py 8 KB
- assets/motionfield_nodes/dwpose_onnx/LICENSE 12 KB
- assets/motionfield_nodes/dwpose_onnx/NOTICE 1 KB
- assets/motionfield_nodes/dwpose_onnx/__init__.py 1 KB
- assets/motionfield_nodes/dwpose_onnx/onnxdet.py 4 KB
- assets/motionfield_nodes/dwpose_onnx/onnxpose.py 12 KB
- assets/motionfield_nodes/dwpose_onnx/wholebody.py 2 KB
- assets/motionfield_nodes/example_workflows/motionfield-director.app.json 20 KB
- assets/motionfield_nodes/example_workflows/motionfield-image.app.json 8 KB
- assets/motionfield_nodes/example_workflows/motionfield-person-swap.app.json 28 KB
- assets/motionfield_nodes/example_workflows/motionfield-reshoot.app.json 20 KB
- assets/motionfield_nodes/example_workflows/motionfield-vfx-lab.app.json 17 KB
- references/agentY-camera-move-control.md 5 KB
- references/requirements.md 9 KB
- scripts/comfy_client.py 8 KB
- scripts/preflight.py 3 KB
- workflows/wan_fun_camera_director.api.json 2 KB
- workflows/wan_fun_camera_director.defaults.json 1 KB
- workflows/wan_fun_camera_i2v.api.json 3 KB
- workflows/wan_fun_camera_i2v.defaults.json 1 KB
- workflows/api/wan21_fun_camera_1_3b.api.json 5 KB
- workflows/api/wan22_14b_fun_camera.api.json 6 KB
- workflows/api/wan_ati_trajectory.api.json 44 KB
- workflows/ui/wan21_fun_camera_1_3b.ui.json 17 KB
- workflows/ui/wan22_14b_fun_camera.ui.json 46 KB
- workflows/ui/wan_ati_trajectory.ui.json 71 KB
Versions
The database has no other skills named camera-control.
Database snapshot: 13.11.2026 · package version d2e84c841523 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90control-to-video
Generate video that follows a control signal (depth, OpenPose skeleton or canny edges extracted from a reference or previs clip) with open-weights LTX-2 and Wan 2.2 Fun Control / Wan VACE in ComfyUI. Use when motion, blocking or layout must match a source clip exactly. - 100blender-cameras
Set up Blender cameras with cinematic intent — focal length, depth of field (f-stop / focus object), composition (rule of thirds, leading lines), animated cameras (orbit, dolly, push-in), tracking constraints. Use whenever the user asks to "set up the camera", "frame the shot",… - 100scene-3d-authoring
Build a 3D scene (a composition whose space is 3d) — models, camera, lighting presets, floor, groups and parenting, model parameters, 3D motion presets (drop_in, fly_in_arc, snap_settle, bounce, idle_bob, wiggle, turntable; camera orbit, dolly, push_in, crane, whip_pan) — then… - 91apple-hig-camera-control
Use when designing or reviewing iPhone Camera Control overlay functions, slider or picker choices, capture-mode availability, or locked capture entry. - 90image-to-3d
Turn a still (or 4 views) into a GLB mesh with open-weights TRELLIS.2 or Pixal3D in ComfyUI. Use for previs props, set pieces and turnaround references. - 100blender-cameras
Set up Blender cameras with cinematic intent — focal length, depth of field (f-stop / focus object), composition (rule of thirds, leading lines), animated cameras (orbit, dolly, push-in), tracking constraints. Use whenever the user asks to "set up the camera", "frame the shot",…