ComfyUI Node
Youtu-VL
A ComfyUI node in 🧪AILab/YoutuVL with 9 inputs and 1 output.
Youtu-VL
- image
- text
◄modelYoutu-VL-4B-Instruct►
◄quantizationNone (FP16)►
◄attention_modeauto►
◄preset_prompt🖼️ Describe Image►
◄custom_prompt►
◄max_tokens512►
◄keep_model_loadedtrue►
◄seed1►
Category🧪AILab/YoutuVL
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | Youtu-VL-4B-Instruct | Select the Youtu-VL model. First run downloads weights to models/LLM/Youtu-VL. |
| quantization | COMBO | None (FP16) | Precision vs VRAM. FP16 gives best quality; 8-bit suits 8-16GB GPUs; 4-bit fits 6GB or less. |
| attention_mode | COMBO | auto | auto tries flash-attn v2 when available, falls back to SDPA. |
| preset_prompt | COMBO | 🖼️ Describe Image | Built-in instruction for how Youtu-VL should analyze the input. |
| custom_prompt | STRING | Optional override - replaces preset template when filled. | |
| max_tokens | INT | 51264–4096 | Maximum number of new tokens to generate. |
| keep_model_loaded | BOOLEAN | true | Keep model in VRAM after run for faster subsequent inference. |
| seed | INT | 11–4294967295 | Seed for reproducible results. |
| imageopt | IMAGE | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |