ComfyUI Node
Prompt Rewriter Options
A ComfyUI node in Prompt Manager with 18 inputs and 1 output.
Prompt Rewriter Options
- image_1
- image_2
- image_3
- image_4
- image_5
- options
◄modelNo models available►
◄gpu_layers►
◄enable_thinkingtrue►
◄context_size4096►
◄max_tokens4096►
◄flash_attentiontrue►
◄system_prompt►
◄use_model_default_samplingfalse►
◄temperature0.80►
◄top_p0.95►
◄top_k40►
◄min_p0.05►
◄repeat_penalty1.00►
CategoryPrompt Manager
Inputs (18)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | No models available | Select model to use. Models with ⬇ will be downloaded automatically. |
| gpu_layers | STRING | GPU layer distribution. Examples: • empty -> All layers go to the first GPU (default) • gpu0:0.7 -> 70% to GPU:0, 30% to CPU • gpu0:0.5, gpu1:0.4 -> 50% GPU:0, 40% GPU:1, 10% CPU | |
| enable_thinking | BOOLEAN | true | Enable thinking/reasoning mode (model thinks before answering) |
| context_size | INT | 4096256–1000000 | Context window size (total tokens for input + output). Higher values use more VRAM. |
| max_tokens | INT | 40961–1000000 | Maximum tokens to generate |
| flash_attention | BOOLEAN | true | Enable Flash Attention for faster inference (recommended: enabled) |
| system_prompt | STRING | Override the default system prompt | |
| use_model_default_sampling | BOOLEAN | false | Use the model's default sampling parameters (overrides temperature, top_p, etc) |
| temperature | FLOAT | 0.800–2 | Temperature for generation (higher = more creative, lower = more focused) |
| top_p | FLOAT | 0.950–1 | Top-p (nucleus) sampling |
| top_k | INT | 400–200 | Top-k sampling (0 = disabled) |
| min_p | FLOAT | 0.050–1 | Min-p sampling threshold |
| repeat_penalty | FLOAT | 1.000–2 | Repetition penalty (1.0 = no penalty, higher = less repetition) |
| image_1opt | IMAGE | Optional image input for VLM models (image 1 of 5). Requires mmproj file. | |
| image_2opt | IMAGE | Optional image input for VLM models (image 2 of 5). Requires mmproj file. | |
| image_3opt | IMAGE | Optional image input for VLM models (image 3 of 5). Requires mmproj file. | |
| image_4opt | IMAGE | Optional image input for VLM models (image 4 of 5). Requires mmproj file. | |
| image_5opt | IMAGE | Optional image input for VLM models (image 5 of 5). Requires mmproj file. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| options | OPTIONS | — |