汇集 FLUX、Stable Diffusion、SDXL 等图像生成模型的训练与微调教程，涵盖 LoRA、DreamBooth、ComfyUI 和云端 Notebook 实操指南。
本地免费运行的一站式 AI 视频与图像编辑工具，集换脸、口型同步、抠图去物、风格重绘、人声分离与克隆、视频生成于一体。
自托管的生成式 AI 网页界面，集成 30 多种模型，覆盖图像、视频、音频生成，用浏览器就能统一调用，省去逐个搭建环境的麻烦。
…erences for Anima, Krea-2 and Qwen-Image-2.1, new ControlNets, much better live previews, faster int8 models, Windows on ARM64, and the return of more features from the l
…ts. ( 881) - mflux-generate-qwen-2.1 , -edit and -controlnet now run Qwen-Image-2.1-Turbo in 8 steps ( --model qwen-image-2.1-turbo ). mflux-save now writes one Qwen-Imag
…ias. ( 839) - New command mflux-generate-qwen-2.1-controlnet : Qwen-Image-2.1 with Alibaba's Fun ControlNet Union. One checkpoint takes Canny, depth, pose and five more k
…s version. ( 728) ( 732) - mflux-generate-z-image-controlnet : --controlnet-strength now defaults to 1.0, so the strength given in each --control spec is the scale the mo
What's Changed fix: fix the ControlNet of Qwen-Image by @wallen0322 in https://github.com/nunchaku-tech/ComfyUI-nunchaku/pull/537 fix: changed device arg to meta for T5XX
…种控制条件下的视频生成 - 工具链升级：发布ppdiffusers 0.29.1版本，新增对SD3 ControlNet和SD3.5的支持。SD3高性能推理性能打平TensorRT。SD3、SDXL模型LoRA训练和推理适配昇腾910B