How do I install the Curated Nunchaku Qwen Lightning Control Net Inpainting skill?

Run npx skillmds@latest add steliosot/curated-nunchaku-qwen-lightning-control-net-inpainting in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Which AI agents work with Curated Nunchaku Qwen Lightning Control Net Inpainting?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Who published Curated Nunchaku Qwen Lightning Control Net Inpainting?

steliosot (@steliosot) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Curated Nunchaku Qwen Lightning Control Net Inpainting by steliosot

Name: Curated Nunchaku Qwen Lightning Control Net Inpainting
Author: steliosot

File contents

curated_nunchaku_qwen_lightning_control_net_inpainting

Curated workflow skill generated from Nunchaku Qwen Lightning + Control Net Inpainting.json.

Capability Family

img2img_inpaint_outpaint

Inputs

Optional runtime overrides supported by run(...):
- prompt
- negative_prompt
- width, height
- seed, steps, cfg
- sampler_name, scheduler, denoise
- server, headers, api_prefix

Outputs

Returns JSON with:
- status
- prompt_id
- output_images (includes image/video entries reported by Comfy history)

Model Requirements

clip: qwen_2.5_vl_7b_fp8_scaled.safetensors -> models/clip
vae: qwen_image_vae.safetensors -> models/vae
controlnet: Qwen-Image-InstantX-ControlNet-Inpainting.safetensors -> models/controlnet

Custom Node Requirements

comfyui-nunchaku
rgthree-comfy

Links Extracted From Workflow Notes

Source

Original: comfy-data/workflows/Nunchaku Qwen Lightning + Control Net Inpainting.json

Routing Metadata

Family: img2img_inpaint_outpaint
Input modalities: image, text_prompt
Output modalities: image/png
Model families: qwen
Node count: 19
Complexity score: 1
Resource profile: low
Estimated runtime: fast (usually under 30s on modern GPU)
Max latent resolution hint: NonexNone
Max sampler steps hint: 4

Detected Models

clip: qwen_2.5_vl_7b_fp8_scaled.safetensors -> models/clip
vae: qwen_image_vae.safetensors -> models/vae
controlnet: Qwen-Image-InstantX-ControlNet-Inpainting.safetensors -> models/controlnet

Detected Custom Nodes

comfyui-nunchaku
rgthree-comfy

Runtime Warnings

Uses custom nodes; missing nodes can cause validation/runtime failures.

---name: curated-nunchaku-qwen-lightning-control-net-inpaintingdescription: Curated ComfyUI workflow imported from `Nunchaku Qwen Lightning + Control Net Inpainting.json`.---# curated_nunchaku_qwen_lightning_control_net_inpaintingCurated workflow skill generated from `Nunchaku Qwen Lightning + Control Net Inpainting.json`.## Capability Family- `img2img_inpaint_outpaint`## Inputs- Optional runtime overrides supported by `run(...)`: - `prompt` - `negative_prompt` - `width`, `height` - `seed`, `steps`, `cfg` - `sampler_name`, `scheduler`, `denoise` - `server`, `headers`, `api_prefix`## Outputs- Returns JSON with: - `status` - `prompt_id` - `output_images` (includes image/video entries reported by Comfy history)## Model Requirements- `clip`: `qwen_2.5_vl_7b_fp8_scaled.safetensors` -> `models/clip`- `vae`: `qwen_image_vae.safetensors` -> `models/vae`- `controlnet`: `Qwen-Image-InstantX-ControlNet-Inpainting.safetensors` -> `models/controlnet`## Custom Node Requirements- `comfyui-nunchaku`- `rgthree-comfy`## Links Extracted From Workflow Notes- https://discord.com/invite/gggpkVgBf3- https://docs.comfy.org/interface/maskeditor- https://github.com/Tavris1/ComfyUI-Easy-Install- https://github.com/nunchaku-tech/ComfyUI-nunchaku- https://huggingface.co/Comfy-Org/Qwen-Image-InstantX-ControlNets/resolve/main/split_files/controlnet/Qwen-Image-InstantX-ControlNet-Inpainting.safetensors- https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors- https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors- https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/text_encoders- https://huggingface.co/nunchaku-tech/nunchaku-qwen-image/resolve/main/svdq-int4_r32-qwen-image-lightningv1.0-4steps.safetensors?download=true- https://huggingface.co/nunchaku-tech/nunchaku-qwen-image/tree/main- https://www.youtube.com/@pixaroma## Source- Original: `comfy-data/workflows/Nunchaku Qwen Lightning + Control Net Inpainting.json`## Routing Metadata- Family: `img2img_inpaint_outpaint`- Input modalities: `image, text_prompt`- Output modalities: `image/png`- Model families: `qwen`- Node count: `19`- Complexity score: `1`- Resource profile: `low`- Estimated runtime: `fast (usually under 30s on modern GPU)`- Max latent resolution hint: `None`x`None`- Max sampler steps hint: `4`## Detected Models- `clip`: `qwen_2.5_vl_7b_fp8_scaled.safetensors` -> `models/clip`- `vae`: `qwen_image_vae.safetensors` -> `models/vae`- `controlnet`: `Qwen-Image-InstantX-ControlNet-Inpainting.safetensors` -> `models/controlnet`## Detected Custom Nodes- `comfyui-nunchaku`- `rgthree-comfy`## Runtime Warnings- Uses custom nodes; missing nodes can cause validation/runtime failures.

Frequently asked questions

Curated Nunchaku Qwen Lightning Control Net Inpainting