run-comfyui-minimax
Release Notes Policy
- A new dated subtitle is added whenever a new stable ComfyUI release is included.
- The date is updated when custom nodes, provisioning or runtime behavior changes.
- Pinned custom nodes are not updated automatically because pin changes can introduce compatibility issues.
- This pod is stable but many custom_nodes and turbo loras are experimental and in full development.
- Tested on L40S, RTX 4090, RTX 3090, RTX 5090 and RTX PRO 6000.
27082026
25082026
- ComfyUI 0.33.0
- Fixed THRESHOLD typo.
- Updated configuration for RTX PRO 6000 for higher quality.
- Changed configuration diffusion model LVRAM BACKWELL for lora compatibility.
- Added local llama-cpp (cli,server) support
- Split runpod prompt enhancement templates for tail and llma-cpp see deployment for more information
- Added uncensored profile to_QWEN_H3_prompt modified workflows.
- Fixed crash mult-shot context pin after first shot in workflows (sol attention)
- ComfyUI-H3-Qwen3VL-TextGen
- MiniMax H3 Audio T8
- ComfyUI_Qwen_H3_Prompt
13082026
11082026
07082026