ComfyUI Node
Simple Qwen-VL Vision Language Model
A ComfyUI node in π SimpleQwenVL with 14 inputs and 4 outputs.
Simple Qwen-VL Vision Language Model
- image
- image2
- image3
- audio
- video
- text
- conditioning
- system_prompt
- user_prompt
βmodel_presetNoneβΊ
βsystem_presetNoneβΊ
βuser_promptDescribe this image.βΊ
βseed42βΊ
βunload_all_modelsfalseβΊ
βmodesubprocessβΊ
βsystem_prompt_overrideββΊ
βconfig_overrideββΊ
βvariablesββΊ
Categoryπ SimpleQwenVL
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| model_preset | COMBO | None | 1 options: None |
| system_preset | COMBO | None | 66 options: None, πΌοΈ Tags, πΌοΈ Simple Description, πΌοΈ Detailed Description, πΌοΈ Ultra Detailed Description, π¬ Cinematic Description, +60 |
| user_prompt | STRING | Describe this image. | β |
| seed | INT | 42 | β |
| unload_all_models | BOOLEAN | false | β |
| mode | COMBO | subprocess | 6 options: subprocess, direct_clean, keep_vram, save1, save2, save3 |
| imageopt | IMAGE | β | |
| image2opt | IMAGE | β | |
| image3opt | IMAGE | β | |
| audioopt | AUDIO | β | |
| videoopt | * | β | |
| system_prompt_overrideopt | STRING | β | |
| config_overrideopt | STRING | β | |
| variablesopt | STRING | β |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| text | STRING | β |
| conditioning | CONDITIONING | β |
| system_prompt | STRING | β |
| user_prompt | STRING | β |