huggingface/diffusers

Support multiple control nets in the `StableDiffusionControlNetXSPipeline`/`StableDiffusionXLControlNetXSPipeline`

Open

#8,434 创建于 2024年6月7日

在 GitHub 查看
 (9 评论) (0 反应) (0 负责人)Python (22,190 star) (4,562 fork)batch import
community-examplescontributions-welcomegood first issue

描述

Is your feature request related to a problem? Please describe. The StableDiffusionControlNetPipeline/StableDiffusionXLControlNetPipeline allow you to specify a list of control nets (i.e. depth and canny)

However, the new ControlNetXS pipelines only allow you provide a single control net

Describe the solution you'd like. I want to be able to do:

vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
canny_controlnet = ControlNetXSAdapter.from_pretrained(
    "UmerHA/Testing-ConrolNetXS-SDXL-canny", torch_dtype=torch.float16
)
depth_controlnet = ControlNetXSAdapter.from_pretrained(
    "UmerHA/Testing-ConrolNetXS-SDXL-depth", torch_dtype=torch.float16
)
pipe = StableDiffusionXLControlNetXSPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", controlnet=[canny_controlnet, depth_controlnet], torch_dtype=torch.float16
)

贡献者指南

技术栈
pythonpytorch
领域
machine learningai
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
half day
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
active
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
PythonPyTorchfamiliarity with diffusers library
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
30
研究方向
Review the existing StableDiffusionControlNetPipeline to understand how it handles a list of controlnets. Examine the ControlNetXS pipeline implementations (StableDiffusionControlNetXSPipeline and StableDiffusionXLControlNetXSPipeline) to identify where to add multiple controlnet support. Focus on the init and forward methods, and ensure that conditional parameters like controlnet conditioning scale are adapted accordingly.