DeepBeepMeep 发布 MiniMax-H3 模型及 WanGP 更新
原标题：DeepBeepMeep/MiniMax-H3
AI 摘要
DeepBeepMeep 在 Hugging Face 发布 MiniMax-H3 图像模型集合，供开源视频生成工具 WanGP 使用。WanGP 支持 Wan、Hunyuan Video、Flux 1/2、Qwen、Z-Image、LTX-2 等模型，最低 6GB 显存即可运行，并兼容旧款 GPU。此次更新新增 TaoMate H3 FL2VA 3-Step 加速配置（rank-128 适配器）和 LightVAE Lite 12 层解码器（BF16 与 INT8 ConvRot 版本）。
正文节选
--- tags: - diffusion-single-file --- You will find here all the MiniMax H3 image models used with WanGP (https://github.com/deepbeepmeep/Wan2GP) : WanGP by DeepBeepMeep : The best Open Source Video Generative Models Accessible to the GPU Poor WanGP supports the Wan (and derived models), Hunyuan Video, Flux 1 & 2, Qwen, Z-Image and LTX-2, LTX Video models with: Low VRAM requirements (as low as 6 GB of VRAM is sufficient for certain models) Support for old GPUs (RTX 10XX, 20xx