v1.0.13 – Qwen3.7 API Support, Safer Vision Model Selection, and Improved Local Cancellation

This release updates Qwen cloud API support and improves model selection safety for vision-only workflows.

Highlights

• Added Qwen3.7 API models:

  • qwen3.7-plus
  • qwen3.7-max
  • qwen3.7-plus-2026-05-26
  • qwen3.7-max-2026-05-20

• Updated Qwen and Wan API defaults to qwen3.7-plus.

• Kept Qwen3.6 and legacy API models selectable for existing workflow compatibility.

• Centralized shared Qwen API model definitions used by Qwen and Wan nodes.

Vision Workflow Handling

• qwen3.7-plus, Qwen3.6, and qwen-vl-* are treated as vision-capable API choices.

• qwen3.7-max remains available for text-only workflows such as:

  • Qwen-Image
  • Wan Text-to-Video

• Text-only API models are hidden from the model dropdown when using:

  • Qwen-Image-Edit
  • Wan Image-to-Video

• The selected model is not automatically changed when switching modes, to avoid unintended API model changes.

• Invalid text-only model selections in vision workflows now show clear ComfyUI execution-block messages instead of runtime tracebacks.

Local GGUF Improvements

• Improved cancellation handling for local GGUF generation.
• Local Qwen, Wan, and Vision LLM runs now propagate ComfyUI interrupt requests more cleanly instead of wrapping them as regular runtime errors.