ComfyUI Node
Eric Qwen Inpaint Prompt Rewriter (Vision)
A ComfyUI node in Eric Qwen-Image with 16 inputs and 1 output.
Eric Qwen Inpaint Prompt Rewriter (Vision)
- image
- mask
- prompt
◄change_description►
◄api_urlhttp://localhost:1234/v1►
◄model►
◄outpaint_description►
◄languageEnglish►
◄temperature0.7►
◄max_tokens2048►
◄outline_color_r255►
◄outline_color_g50►
◄outline_color_b50►
◄outline_width3►
◄custom_instructions►
◄passthroughfalse►
◄image_max_side1024►
CategoryEric Qwen-Image
Inputs (16)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | Source image for the VLM to analyse. | |
| change_description | STRING | Describe what you want to change in the masked area. Example: 'Replace the car with a green taxi' Example: 'Change the sky to a dramatic sunset' | |
| api_url | STRING | http://localhost:1234/v1 | OpenAI-compatible vision API URL. LM Studio: http://localhost:1234/v1 Ollama: http://localhost:11434/v1 OpenAI: https://api.openai.com/v1 |
| modelopt | STRING | Model name override. Leave empty to auto-detect the loaded model from the API server. Ollama: qwen3-vl, qwen2.5-vl:7b OpenAI: gpt-4o-mini, gpt-4o | |
| maskopt | MASK | Inpaint mask (white = area to change). A red outline will be drawn on the image for the VLM. Not needed for outpainting. | |
| outpaint_descriptionopt | STRING | What to add in the outpaint expansion area. Example: 'Mountain landscape extending into the distance' Only used when no mask is provided or when you want outpainting context in the prompt. | |
| languageopt | COMBO | English | Language for the rewritten prompt. |
| temperatureopt | FLOAT | 0.70–2 | VLM temperature. Lower = more faithful. |
| max_tokensopt | INT | 2048256–8192 | Max tokens for the VLM response. |
| outline_color_ropt | INT | 2550–255 | Mask outline red channel. |
| outline_color_gopt | INT | 500–255 | Mask outline green channel. |
| outline_color_bopt | INT | 500–255 | Mask outline blue channel. |
| outline_widthopt | INT | 31–10 | Pixel width of the mask outline. |
| custom_instructionsopt | STRING | Additional instructions for the VLM. Example: 'Use a cinematic photography style' Appended to the system prompt. | |
| passthroughopt | BOOLEAN | false | Skip VLM rewriting. Passes change_description through as-is (for A/B testing). |
| image_max_sideopt | INT | 1024256–2048 | Max pixel size (longest side) for the image sent to the VLM. Larger = more detail but slower and more tokens. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| prompt | STRING | — |