ComfyUI Node
🖼️ AITEC LLM Vision
A ComfyUI node in AITEC/LocalLLM with 15 inputs and 3 outputs.
🖼️ AITEC LLM Vision
- model
- image1
- image2
- image3
- image4
- text
- used_model
- status
◄system_promptYou are a helpful assistant.►
◄promptDescribe the image(s) in detail.►
◄temperature0.70►
◄top_p0.95►
◄max_tokens4096►
◄remove_thinktrue►
◄remove_chatmltrue►
◄suppress_thinkingfalse►
◄unload_after_runtrue►
◄seed0►
CategoryAITEC/LocalLLM
Inputs (15)
| Name | Type | Default | Description |
|---|---|---|---|
| model | LLM_MODEL | — | |
| system_prompt | STRING | You are a helpful assistant. | — |
| prompt | STRING | Describe the image(s) in detail. | — |
| temperature | FLOAT | 0.700–2 | — |
| top_p | FLOAT | 0.950–1 | — |
| max_tokens | INT | 409664–32768 | Thinking model with 4096 or more is recommended |
| remove_think | BOOLEAN | true | Remove the <think>...</think> block (Qwen3, Gemma4, etc.) |
| remove_chatml | BOOLEAN | true | Remove repetitions of <|im_start|>assistant～<|im_end|> and return only the first response (Gemma4, etc.) |
| suppress_thinking | BOOLEAN | false | When enabled, adds an inference suppression instruction to the system prompt (for Thinking models such as Qwen3 and Gemma4) |
| unload_after_run | BOOLEAN | true | Unload the model after execution to free up VRAM. You will need to reload it when you run it again. |
| seed | INT | 00–18446744073709550000 | Changing the value each time the code runs bypasses the cache and forces a re-execution. |
| image1opt | IMAGE | — | |
| image2opt | IMAGE | — | |
| image3opt | IMAGE | — | |
| image4opt | IMAGE | — |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |
| used_model | STRING | — |
| status | STRING | — |