ComfyUI Node Runs on cloud
Judge Images
Score each picture in a batch, as several seeds of one prompt make, from 0 to 10 with a language model that reads them. Edits are scored on following, consistency and quality against their source; generations on following and quality. Hands on the best and its notes.
Judge Images
- clip
- images
- source
- best
- index
- passed
- scores
- notes
◄prompt►
◄least_following9►
◄least_consistency8►
◄least_quality6►
CategoryWAS Suite/Image/Analyze
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | qwen3.5_9b_int8_convrot.safetensors from Load CLIP with type krea2, or another Qwen-VL model. | |
| images | IMAGE | The pictures to score, 1 to 6, as VAE Decode gives a batch from Repeat Latent Batch. | |
| prompt | STRING | The instruction the edits followed or the prompt the pictures came from, as 'Make it snow'. | |
| least_following | INT | 90–10 | The following score a picture needs to pass, 0 to 10. |
| least_consistency | INT | 80–10 | The consistency score an edit needs to pass, 0 to 10. Unused without a source. |
| least_quality | INT | 60–10 | The quality score a picture needs to pass, 0 to 10. |
| sourceopt | IMAGE | The picture before the edit. Unwired = the pictures are judged as generations. |
Outputs (5)
| Name | Type | Description |
|---|---|---|
| best | IMAGE | The picture kept: the best that passes, or the best of all when none does. |
| index | INT | The kept picture's place in the batch, from 0. |
| passed | BOOLEAN | True when the kept picture reaches every least score. |
| scores | STRING | Every picture's scores and notes as a JSON list, in batch order. |
| notes | STRING | The flaws found in the kept picture, for Generate Edit Instruction's feedback. |