ComfyUI Node
Vision LLM Judge
A ComfyUI node in Kinburg-Nodes/LLM with 10 inputs and 4 outputs.
Vision LLM Judge
- config
- images
- summary
- results_json
- best_index
- help
◄rubricRate the overall image quality: anatomy/structure, sharpness and detail, and how well it matches the prompt. Penalize artifacts, extra or malformed limbs/fingers, and watermarks.►
◄prompts—►
◄score_min1►
◄score_max5►
◄unload_after_runconfig default►
◄criteriaoverall_quality: style matches the prompt, no artifacts, no excess noise, correct proportions, good color reproduction
anatomy: all required limbs present, no extra limbs, correct placement, natural pose, proportional body
prompt_compliance: how accurately the image follows the generation prompt
camera: camera angle and camera settings match the intent
text: if the prompt requests text — present, character-accurate, correct color/font/size/placement (if the prompt has NO text, give the top score)►
◄system_promptYou are a strict, consistent image-quality judge. You are shown ONE image plus evaluation criteria. Assess the image only against those criteria and be objective. Reply with ONLY a single JSON object — no prose, no markdown, no code fences.►
◄comment_styleone concise sentence►
CategoryKinburg-Nodes/LLM
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| config | KINBURG_LLM_CONFIG | A 'Local LLM Settings (GGUF)' node WITH a 'Vision Settings (GGUF)' (mmproj) attached. The judge needs vision. | |
| images | IMAGE | Images to judge — a batch OR an image list (mixed sizes fine). | |
| rubric | STRING | Rate the overall image quality: anatomy/structure, sharpness and detail, and how well it matches the prompt. Penalize artifacts, extra or malformed limbs/fingers, and watermarks. | What to judge each image on. Be concrete. |
| promptsopt | STRING | Optional per-image generation prompts, '---'-separated blocks (e.g. Get Accumulator (prompts)). Lets the judge assess prompt adherence. | |
| score_minopt | INT | 10–100 | Lowest score on the scale. |
| score_maxopt | INT | 51–100 | Highest score on the scale. |
| unload_after_runopt | COMBO | config default | Free the model from VRAM after THIS node runs, without touching the shared config. 'config default' follows the Settings node; 'unload after run' frees VRAM before your image generation; 'keep loaded' stays warm. |
| criteriaopt | STRING | overall_quality: style matches the prompt, no artifacts, no excess noise, correct proportions, good color reproduction anatomy: all required limbs present, no extra limbs, correct placement, natural pose, proportional body prompt_compliance: how accurately the image follows the generation prompt camera: camera angle and camera settings match the intent text: if the prompt requests text — present, character-accurate, correct color/font/size/placement (if the prompt has NO text, give the top score) | Multi-criteria mode: one criterion per line, 'name' or 'name: what it means'. The judge scores EACH on the score scale and the overall score is their average. Pre-filled with an example — edit it, or CLEAR it for a single overall score. |
| system_promptopt | STRING | You are a strict, consistent image-quality judge. You are shown ONE image plus evaluation criteria. Assess the image only against those criteria and be objective. Reply with ONLY a single JSON object — no prose, no markdown, no code fences. | Who the judge is (the model's system prompt). The built-in default is shown — edit to change persona/strictness. Cleared → falls back to the built-in default. |
| comment_styleopt | STRING | one concise sentence | How the 'comment' field should read, inserted into the JSON instruction. Default 'one concise sentence'; e.g. 'two to four sentences covering strengths and weaknesses' for a detailed review (raise the Settings max_tokens for long comments). |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| summary | STRING | — |
| results_json | STRING | — |
| best_index | INT | — |
| help | STRING | — |