ComfyUI Node
Unified Vision Prompt Generator
A ComfyUI node in GraftingRayman/Image Processing with 7 inputs and 1 output.
Unified Vision Prompt Generator
- image
- prompt
◄questionDescribe this image in detail.►
◄max_new_tokens1024►
◄temperature0.7►
◄seed1►
◄modelQwen/Qwen2.5-VL-7B-Instruct►
◄keep_model_loadedfalse►
CategoryGraftingRayman/Image Processing
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| question | STRING | Describe this image in detail. | — |
| max_new_tokens | INT | 10241–4096 | — |
| temperature | FLOAT | 0.70–2 | — |
| seed | INT | 11–18446744073709550000 | — |
| model | COMBO | Qwen/Qwen2.5-VL-7B-Instruct | 10 options: Qwen/Qwen2-VL-2B-Instruct, Qwen/Qwen2-VL-7B-Instruct, Qwen/Qwen2.5-VL-3B-Instruct, Qwen/Qwen2.5-VL-7B-Instruct, Qwen/Qwen2.5-VL-72B-Instruct, vikhyatk/moondream2, +4 |
| keep_model_loaded | BOOLEAN | false | — |
| imageopt | IMAGE | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| prompt | STRING | — |