ComfyUI Node
Prompt & Dimensions from LLM
Resolves a diffusion prompt and target image size from an LLM JSON hint {rewritten_prompt, wh_ratio, ratio_follow}. Either wh_ratio (used with megapixels) or ratio_follow (an uploaded image's size) determines dimensions; at least one is required.
Prompt & Dimensions from LLM
- images
- prompt
- width
- height
◄llm_prompt—►
◄megapixels1.0►
◄multiple8►
Categoryprompt/resolve
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| llm_prompt | STRING | JSON hint generated by the LLM. | |
| megapixels | FLOAT | 1.00.1–16 | Target size in megapixels (0.1-16.0). Only used when wh_ratio is provided; ignored when ratio_follow is used. |
| multiple | INT | 88–128 | Pixel grid that resolved width/height are rounded up to (default 8). Only used when wh_ratio is provided. |
| images | COMFY_AUTOGROW_V3 | Up to 10 reference images. ratio_follow can name one of them (e.g. '<image1>') to reuse its exact size. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| prompt | STRING | — |
| width | INT | — |
| height | INT | — |