MiniMax H3 Image原生支持ComfyUI
Comfy Blog报道，MiniMax H3 Image现已原生支持ComfyUI，用户可下载开放权重在本地GPU运行，也可通过Partner Nodes调用API。同一检查点同时支持文生图与参考图编辑，并可使用编号输入进行多参考图编辑。Comfy Blog称，该CFG蒸馏模型固定采用6步采样、guidance为1，并原生支持最高4096×4096及多种宽高比输出。
这项集成让用户能在ComfyUI中直接使用MiniMax的开放权重图像模型，并结合本地部署与API工作流完成生成和编辑。
MiniMax H3 Image is now supported natively in ComfyUI. Open weights, six sampling steps, and output at 4096×4096. One model covers text-to-image and reference-image editing. It runs on your own hardware, and it is also available via Partner Nodes.
Model Introduction
MiniMax H3 Image is MiniMax’s open-weights image model. It generates from a prompt, and it edits when you hand it reference images. Same checkpoint, same graph. A run with images connected is an image edit workflow. A run without is text-to-image.
It shares its Qwen3-VL text encoder with MiniMax H3, the video model already supported in ComfyUI. If you run MiniMax H3 today, you already have that file.
The model is CFG-distilled and samples in six steps at guidance 1. Those values are fixed by the checkpoint, so there is nothing to tune and no negative prompt to write.
There are two ways to run it in ComfyUI:
#MiniMax H3 Image#ComfyUI#MiniMax#MiniMax H3#Qwen3-VL#MiniMax H3 Image Prompt Enhancer