MiniMax-H3 Prompt-Rewriter (Qwen3.8-27B)
Prompt-rewriter models built on Qwen3.8-27B:
- lightx2v/MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-FL2VA
- lightx2v/MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VA
Using in ComfyUI
These models can be used with the ComfyUI-QwenVL (Separate branch with changes) nodes as prompt enhancers via the QwenVL (GGUF) node. Or any other LLM lora loaders.
An example workflow is available here: Q3.8_27B_H3_promt_enhance.json.
The loras are converted to GGUF on the fly during runtime, so no manual conversion step is needed just point the node at the .safetensors file.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support