v1.0.14 – llama-cpp-python MTMD Compatibility Fix

Fixed local Qwen GGUF vision handler initialization with recent JamePeng llama-cpp-python builds

Added runtime compatibility for MTMD handlers that expect mmproj_path
Preserved compatibility with older builds that still require clip_model_path
Prevented Qwen3-VL and Qwen3.5/3.6 local vision runs from falling back to text-only mode because of the handler keyword mismatch

Improved mmproj logging for local Qwen vision models

Reports the selected mmproj after manual selection or auto-detection
Avoids printing Using mmproj: None for text-only paths

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.

v1.0.12 – Qwen API Deprecation Handling and Qwen3.6 Cloud Model Updates

This release updates the cloud Qwen API model list in response to Alibaba Cloud Model Studio deprecation notices, while keeping existing workflows compatible.

What's Changed

• Prioritized Qwen3.6 cloud API models in Qwen and Wan prompt generator nodes

  • Added qwen3.6-plus
  • Added qwen3.6-flash
  • Added Qwen3.6 dated/model-size variants

• Kept legacy Qwen API models selectable for existing workflow compatibility

  • Models announced offline since 2026-05-13 are marked as deprecated in the UI
  • Models scheduled to go offline on 2026-07-13 are marked separately
  • Other legacy models are marked with a recommendation to prefer Qwen3.6

• Improved API model handling

  • Annotated UI labels are normalized before being sent to DashScope
  • Qwen Image Edit API defaults now use qwen3.6-plus
  • Wan Image-to-Video API validation now allows Qwen3.6 vision-capable models in addition to qwen-vl-*

• Updated documentation

  • README upgrade notes now document the Qwen API model deprecation handling
  • Changelog updated for v1.0.12

Notes

Existing workflows using older Qwen API model IDs should continue to load. For new workflows, qwen3.6-plus or qwen3.6-flash is recommended.

v1.0.11 – Qwen3.6 Support and GGUF Discovery Improvements

This release adds Qwen3.6 local GGUF support and improves GGUF model discovery for users who store models outside the default ComfyUI models directory.

Added

• Added support for Qwen3.6 local GGUF models
  • Detects qwen36 and qwen3.6 model filenames
  • Routes Qwen3.6 through the existing Qwen35ChatHandler path
  • Updates Qwen3.5/3.6 mmproj requirement messages and logging

Improved

• Improved local GGUF model discovery

  • Models registered through ComfyUI extra_model_paths.yaml are now discovered
  • External model paths, including paths on another drive, are preserved as absolute paths
  • Thanks to @bongobongo2020 for this contribution

• Improved mmproj auto-detection

  • If no family-prefixed mmproj matches but the model directory contains exactly one mmproj-*.gguf, that file is now selected automatically
  • Ambiguous cases with multiple unmatched mmproj files still require manual selection
  • Thanks to @bongobongo2020 for this contribution

Documentation

• Updated README and CHANGELOG for v1.0.11

v1.0.10 – Qwen3.5 Support and Stability Improvements

Added local GGUF support for Qwen3.5 models

• Implemented proper Qwen3.5 handler routing with Qwen35ChatHandler
• Fixed incorrect fallback to Qwen3VLChatHandler for Qwen3.5 model names
• Improved mmproj handling for Qwen3.5 (requirement checks + auto-detection flow)

Added post-run cleanup() calls to VisionLLMNode, WanVideoPromptGenerator, and QwenImageEditPromptGenerator

• Refined cleanup lifecycle with cleanup(finalize=False/True) for regular unload vs final teardown

v1.0.9 - Local GGUF Discovery Expansion, mmproj Filtering, and Qwen/Wan Prompt Quality Improvements

Highlights

This release focuses on four major areas:

• Expanded local GGUF model discovery
• Safer and more intuitive mmproj selection
• Improved Qwen / Wan prompt rewriting quality
• Better robustness for text-only and image-to-video workflows

What Changed

Local GGUF model discovery

• Expanded local Qwen-family GGUF model search paths
• Added models/text_encoders and all subdirectories under both models/LLM and models/text_encoders to the search paths
• Centralized local model path and mmproj path resolution in local_gguf_utils.py
• Reduced duplicated path-handling logic across nodes

mmproj handling and model selection

• Added UI-side mmproj filtering so only mmproj files in the same directory as the selected model are shown
• Improved mmproj resolution behavior for local models
• Explicitly forces text-only mode when mmproj = (Not required) is selected
• Prevents unnecessary or incorrect Vision handler usage in text-only workflows
• Improves safety when switching between local model configurations

Prompt rewriting quality

• Added dedicated system prompt flows for:
  • qwen_image
  • qwen_image_edit
  • wan_t2v
  • wan_i2v
• Strengthened prompt instructions so outputs are more likely to contain only the final prompt body
• Reduced verbose analysis-style or heading-based outputs
• Added a second-pass Simplified Chinese normalization flow when Chinese output is requested but another language is returned
• Preserves quoted text during second-pass normalization to avoid breaking user-specified text
• Improved Qwen2.5-VL behavior in Qwen Image Edit Prompt Generator by fixing system prompt application issues

Node behavior and robustness

• Qwen-Image can now be used without an image input for text-only prompt generation
• Local text-only Qwen-Image runs no longer require mmproj
• Increased local inference max_tokens and n_ctx for longer prompt generation
• Added explicit validation for missing image input in Image-to-Video mode
• Improved output control for Wan prompt generation in Chinese-targeted workflows

Upgrade Notes

• After upgrading, you may need to reselect your GGUF model and mmproj file once
• This is because internal model path handling changed with the expanded search paths
• If you use local GGUF models, verify that the selected mmproj still matches the model directory
• Users of Qwen Image Edit Prompt Generator with Qwen2.5-VL should see improved output quality in this release

Notes

• Vision behavior still depends on the installed llama-cpp-python build and backend environment
• Some models may still show different output quality depending on whether they are used locally or via API
• Chinese-targeted prompt generation should now be more stable, but final output quality still depends on model behavior

v1.0.8 - Bug Fix

• Fixed issue where Qwen2.5-VL were always loaded in text-only mode even when a valid mmproj file was specified.
• Improved mmproj auto-detection logic."

v1.0.7 - Stability Update

• Fixed incorrect detection of Qwen3-VL when mmproj is set to (Not required).
  • Disabled automatic mmproj detection and prevented use of the VL handler in this case.
  • Updated GGUFModelManager.load_model and node-side mmproj interpretation to correctly respect (Not required).

v1.0.6 – Stability and Documentation Update

This release focuses on stability improvements and documentation cleanup ahead of the initial Comfy Registry publishing.

Changes

• Improved stability when switching between Qwen3-VL GGUF models
• Fixed mmproj reuse issues in local vision models
• Refined internal GGUF model lifecycle management
• Clarified project scope as a prompt generator for QwenImageEdit and Wan2.2
• Reorganized Credits and Dependencies for clearer attribution
• Updated llama-cpp-python installation notes to reference the JamePeng fork documentation

Notes

• No breaking changes to node interfaces
• This is the first version published to the Comfy Registry

v1.0.5 - Initial Release

v1.0.5 - Initial Release

Multimodal prompt generation nodes for ComfyUI with local Qwen-VL GGUF support.

What's Included

• Vision LLM Node - Local GGUF models (Qwen2.5-VL, Qwen3-VL) with multi-image input
• Qwen Image Edit - Image editing prompt optimization (local + cloud API)
• Wan Video Generator - T2V/I2V prompt enhancement for Wan2.2

Key Features

✅ Multi-image batch input support
✅ CPU/GPU device selection
✅ 5 style presets (raw, default, detailed, concise, creative)
✅ Auto-detect mmproj for Qwen3-VL
✅ Optimized for Chinese language prompts
✅ GPL-3.0 licensed with proper attribution

Installation

cd ComfyUI/custom_nodes
git clone https://github.com/kantan-kanto/ComfyUI-MultiModal-Prompt-Nodes.git
cd ComfyUI-MultiModal-Prompt-Nodes
pip install -r requirements.txt

Full documentation: README.md