菜单
Use this skill when working with the lightflow.flux_inpaint workflow, masks, local repainting, or FLUX inpaint model sync.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use this skill when working with the lightflow.flux_image_edit workflow, prompt-guided image editing, or FLUX image-edit model sync.
Use this skill when working with the lightflow.flux_preview_text_to_image deterministic preview workflow or testing FLUX pipelines without a model backend.
Use this skill when working with the lightflow.flux_text_to_image workflow, syncing FLUX models, or generating images from prompts.
Use this skill when working with the lightflow.flux_text_to_image_router workflow or routing image generation between real FLUX and preview runtimes.
| name | LightFlow FLUX Inpaint |
| description | Use this skill when working with the lightflow.flux_inpaint workflow, masks, local repainting, or FLUX inpaint model sync. |
| version | 0.1.0 |
Use lightflow.flux_inpaint for masked local repainting with a PNG mask.
lightflow.flux_inpaintimage_path, mask_path, prompt, negative, strength, feather_px, dilate_px, invert_mask, seed, count, steps, guidance, output_path, output_template, model.image, image_path, images, image_paths.lightflow.image.inpaint.flux_model, llm_model, and vae_model.image_path is an image artifact input, mask_path is a mask artifact input, image outputs are image artifacts, and sampling/mask controls expose editor ranges.White mask pixels are repainted, black pixels are preserved, and gray values are soft weights. Set invert_mask=true to flip that convention.
feather_px and dilate_px are preprocessing hints. Keep mask_path in the same coordinate space as image_path; resizing or composing masks should be done by upstream mask nodes.
Run lfw sync lightflow.flux_inpaint --auto-model --apply before a real inpaint run. The runtime uses flux-native when available, otherwise LIGHTFLOW_FLUX_RUNNER receives --task inpaint, source image path, mask path, prompt, model paths, and output path.
lfw sync lightflow.flux_inpaint --auto-model --apply
lfw run lightflow.flux_inpaint \
-i image_path='"input.png"' \
-i mask_path='"mask.png"' \
-i prompt='"repair the scratched area"' \
-i output_path='"out/inpaint.png"'
lfw node test lightflow.flux_inpaint
Start lfw serve, then call the workflow through the shared HTTP run contract. Adjust inputs to match the workflow contract above.
curl -sS -X POST http://127.0.0.1:5174/workflows/lightflow.flux_inpaint/run \
-H 'content-type: application/json' \
-d '{"inputs":{}}'