ComfyUI Node
Claude Vision Analysis
Analyze images using Claude's multimodal vision capabilities.
Claude Vision Analysis
- image
- client
- additional_images
- analysis
◄questionDescribe this image in detail.►
◄seed-1►
◄model(inherit from client)►
◄detail_levelhigh►
◄max_tokens2048►
CategoryERPK/Claude
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | Primary image to analyze (ComfyUI tensor) | |
| question | STRING | Describe this image in detail. | Question or instruction about the image(s) |
| seed | INT | -1-1–2147483647 | Seed for cache control. Randomizes by default to ensure fresh results each run. |
| clientopt | CLAUDE_API_CLIENT | Claude API client (optional if API key is configured in Settings) | |
| modelopt | COMBO | (inherit from client) | Override the client's model for this vision call. Opus 4.7 supports 2576px image resolution (vs 1568px on prior models). |
| additional_imagesopt | IMAGE | Optional additional images (up to 19 more, for 20 total) | |
| detail_levelopt | COMBO | high | Level of detail in analysis |
| max_tokensopt | INT | 2048256–4096 | Maximum length of analysis |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| analysis | STRING | — |