ComfyUI Node
✨ Auto-LLM-Text-Vision
A ComfyUI node in 🧩 Auto-Prompt-LLM with 24 inputs and 7 outputs.
✨ Auto-LLM-Text-Vision
- clip
- image_to_llm_vision
- postive
- negative
- orignal-postive
- orignal-negative
- 🌀LLM-Text
- 🌀LLM-Vision
- 🌀postive+LLM-Text+LLM-Vision
◄is_trigger_every_generatedtrue►
◄llm_text_result_append_enabledtrue►
◄llm_vision_result_append_enabledtrue►
◄text_prompt_postive1girl,►
◄text_prompt_negative—►
◄llm_keep_your_prompt_aheadtrue►
◄llm_recursive_usefalse►
◄llm_apiurlhttp://localhost:1234/v1/chat/completions►
◄llm_apikeylm-studio►
◄llm_api_model_namellama3.1►
◄llm_text_max_token50►
◄llm_text_tempture0.30►
◄llm_text_system_promptYou are an AI prompt word engineer. Use the provided keywords to create a beautiful composition. Only the prompt words are needed, not your feelings. Customize the style, scene, decoration, etc., and be as detailed as possible without endings.►
◄llm_text_ur_promptA superstar on stage.►
◄llm_vision_max_token50►
◄llm_vision_tempture0.80►
◄llm_vision_system_promptThis is a chat between a user and an assistant. The assistant is helping the user to describe an image.►
◄llm_vision_ur_promptWhat's in this image?►
◄llm_before_action_cmd_feedback_type▾►
◄llm_before_action_cmd►
◄llm_post_action_cmd_feedback_type▾►
◄llm_post_action_cmd►
Category🧩 Auto-Prompt-LLM
Inputs (24)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | — | |
| image_to_llm_vision | IMAGE | — | |
| is_trigger_every_generated | BOOLEAN | true | — |
| llm_text_result_append_enabled | BOOLEAN | true | — |
| llm_vision_result_append_enabled | BOOLEAN | true | — |
| text_prompt_postive | STRING | 1girl, | — |
| text_prompt_negative | STRING | — | |
| llm_keep_your_prompt_ahead | BOOLEAN | true | — |
| llm_recursive_use | BOOLEAN | false | — |
| llm_apiurl | STRING | http://localhost:1234/v1/chat/completions | — |
| llm_apikey | STRING | lm-studio | — |
| llm_api_model_name | STRING | llama3.1 | — |
| llm_text_max_token | INT | 5010–1024 | — |
| llm_text_tempture | FLOAT | 0.30-2–2 | — |
| llm_text_system_prompt | STRING | You are an AI prompt word engineer. Use the provided keywords to create a beautiful composition. Only the prompt words are needed, not your feelings. Customize the style, scene, decoration, etc., and be as detailed as possible without endings. | — |
| llm_text_ur_prompt | STRING | A superstar on stage. | — |
| llm_vision_max_token | INT | 5010–1024 | — |
| llm_vision_tempture | FLOAT | 0.80-2–2 | — |
| llm_vision_system_prompt | STRING | This is a chat between a user and an assistant. The assistant is helping the user to describe an image. | — |
| llm_vision_ur_prompt | STRING | What's in this image? | — |
| llm_before_action_cmd_feedback_type | COMBO | 4 options: Pass, just-call, LLM-USER-PROMPT, LLM-VISION-IMG_PATH | |
| llm_before_action_cmd | STRING | — | |
| llm_post_action_cmd_feedback_type | COMBO | 4 options: Pass, just-call, LLM-USER-PROMPT, LLM-VISION-IMG_PATH | |
| llm_post_action_cmd | STRING | — |
Outputs (7)
| Name | Type | Description |
|---|---|---|
| postive | CONDITIONING | — |
| negative | CONDITIONING | — |
| orignal-postive | STRING | — |
| orignal-negative | STRING | — |
| 🌀LLM-Text | STRING | — |
| 🌀LLM-Vision | STRING | — |
| 🌀postive+LLM-Text+LLM-Vision | STRING | — |