image-edit
Installation
SKILL.md
image-edit
Run every graph with the bundled client: python scripts/comfy_client.py --url $COMFY_URL run workflows/<file> --set NODE.INPUT=VALUE --out out/. Upload input files first with python scripts/comfy_client.py upload <file>. Before the first run on a server, check it with python scripts/preflight.py --url $COMFY_URL workflows/<file>. Node packs, model files, VRAM and weight licenses for this skill are in references/requirements.md. Use open-weights models only, and never swap in a hosted or closed model.
Pick a graph
| Request | Workflow | Set |
|---|---|---|
| Any instruction edit ("make her coat red") | qwen_edit_2511_instruct.api.json |
41.image, 100.prompt, 106.seed |
| New camera angle (2511 multi-angle LoRA) | qwen_edit_2511_angles.api.json |
41.image, angle words go into the 120-122 string chain (<sks> trigger) |
| Rotate the camera, fast (8-step Lightning) | qwen_edit_2509_angle_lightning.api.json |
img1.image, pos.prompt |
| Push in / close-up coverage | qwen_edit_2509_pushin_lightning.api.json, qwen_edit_2509_coverage_lightning.api.json |
img1.image, pos.prompt |
| Relight (time of day, key light) | qwen_edit_2509_relight.api.json |
1.image, 11.prompt |
| Virtual try-on (person + garment image) | qwen_edit_2511_try_on.api.json |
41.image person, 83.image garment, 149.prompt, 169.seed |
| Four-angle set in one run | qwen_edit_2511_angles_set.api.json |
41.image; angle words in 1120/2120/3120/4120 .string_a |
| Edit one layer (Qwen layered) | qwen_edit_2511_layers_edit.api.json |
1.image, 13.prompt, 18.seed |
| Outpaint to a new aspect | qwen_image_outpaint_format.api.json |
1.image, 7/8 aspect W:H, 9 long side, 37.text |