What Anthropic Claude is good at
- Strong reasoning: A model family known for strong reasoning, safety, and long-context capabilities
- Conversational and image analysis tasks: Use Claude directly inside your ComfyUI workflows through Partner Nodes
- Multimodal input: Every supported model accepts text-only and text + image inputs, with up to 20 images per request
- A model for every workload: From the flagship Opus line to fast, cost-effective Haiku for high-throughput use cases
Supported Models
All models support both text-only and multimodal (text + image) inputs with up to 20 images per request.
Anthropic Claude Chat Workflow
Run on Comfy Cloud
Open in Comfy Cloud
Download Workflow
Download JSON or search “Anthropic Claude” in Template Library
In the corresponding template, we have built a prompt for analyzing and generating role prompts, used to interpret your images into corresponding drawing prompts.
- In the
Load Imagenode, load the image you need AI to interpret (optional: skip for text-only queries) - In the
Anthropic Claudenode, modifypromptto set your conversation prompt, or changemodelto select a different Claude model - (Optional) Set the
system_promptto define the model’s behavioral instructions - Click
Runor pressCtrl(cmd) + Enterto execute the conversation - After the API returns results, view the AI response in the
Preview Anynode
Additional Notes
- Adjust
max_tokens(up to 32768) andtemperature(0.0 to 1.0) in the node’s advanced options.temperatureis unavailable when thinking is enabled, or onOpus 4.7 - The
seedparameter controls whether the node re-runs: results are non-deterministic regardless of seed value
Claude Fable 5.1 Workflow
Run Claude Fable 5.1, Anthropic’s advanced reasoning model, directly in your workflow for long-running, multi-step problems. Fable 5.1 always runs with thinking enabled and does not expose atemperature control.
Run on Comfy Cloud
Open in Comfy Cloud
Download Workflow
Download JSON or search “Claude: Fable 5.1” in Template Library
Input Image: blue_poppies_field.png
Image for the workflow, or use your own image.
- In the
Load Imagenode, load the image you need AI to interpret (optional: skip for text-only queries) - In the
Anthropic Claudenode, modifypromptto set your conversation prompt. The model is preset toFable 5.1with a 32768max_tokenslimit - Click
Runor pressCtrl(cmd) + Enterto execute the conversation - After the API returns results, view the AI response in the
Preview Anynode