ComfyUI Node
Ollama Video Analyze
Sample frames from a video and analyze them with an Ollama vision model. Works with any IMAGE batch representing a frame sequence.
Ollama Video Analyze
- frames
- connectivity
- options
- meta
- result
- thinking
- meta
◄promptDescribe what happens in this video clip.►
◄max_frames8►
◄sample_mode▾►
◄systemYou are analyzing frames sampled from a video clip. Describe the action, subjects, and content.►
◄thinkfalse►
◄format▾►
CategoryOllama/Video
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| frames | IMAGE | Video frames as an IMAGE batch (e.g. from VHS Load Video or any frame sequence node). | |
| prompt | STRING | Describe what happens in this video clip. | Prompt for the vision model. |
| max_frames | INT | 81–64 | Maximum frames to sample and send. More = richer context but slower and higher memory. |
| sample_mode | COMBO | Sampling strategy: uniform=evenly spaced across entire clip, first=opening frames, last=closing frames. | |
| systemopt | STRING | You are analyzing frames sampled from a video clip. Describe the action, subjects, and content. | System prompt for the model. |
| thinkopt | BOOLEAN | false | Enable chain-of-thought reasoning (model must support this). |
| formatopt | COMBO | Output format. | |
| connectivityopt | OLLAMA_CONNECTIVITY | — | |
| optionsopt | OLLAMA_OPTIONS | — | |
| metaopt | OLLAMA_META | — |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| result | STRING | — |
| thinking | STRING | — |
| meta | OLLAMA_META | — |