pipeline_stable_diffusion_xl_instanti... pipeline_stable_diffusion_xl_instantid.py 39.20 KB 一键复制 编辑 原始数据 按行查看 历史 InstantX 提交于 12个月前 . Merge pull request #55 from InstantID/ip_adapter_scale 12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535...
class StableDiffusionXLInstantIDImg2ImgPipeline(StableDiffusionXLControlNetImg2ImgPipeline): def cuda(self, dtype=torch.float16, use_xformers=False): self.to("cuda", dtype)if hasattr(self, "image_proj_model"): self.image_proj_model.to(self.unet.device).to(self.unet.dtype)...
StableDiffusionXLInstantIDImg2ImgPipeline中749行的self.check_inputs多了两个None Member haofanwang commented Jul 27, 2024 应该是diffusers官方参数有更新,可以将pipeline中的参数按名字指定 Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment Assignees ...
#OneDiff #Stable Diffusion * SDXL 和 SVD 的 SOTA 性能更新* 全面支持SD、SVD动态分辨率运行* 编译/保存/加载HF Diffusers的pipeline* HF Diffusers的快速 LoRA 加载和切换* 加速了 InstantID(加速1.8 倍)* 加速了 SDXL LightningGitHub:链接性能对比详情:链接 发布于 2024-03-08 09:20・IP 属地北京 ...
class StableDiffusionXLInstantIDPipeline(StableDiffusionXLControlNetPipeline): def cuda(self, dtype=torch.float16, use_xformers=False): self.to('cuda', dtype) if hasattr(self, 'image_proj_model'): self.image_proj_model.to(self.unet.device).to(self.unet.dtype) if use_xformers: ...
>>> from pipeline_stable_diffusion_xl_instantid import StableDiffusionXLInstantIDPipeline, draw_kps >>> # download 'antelopev2' under ./models >>> app = FaceAnalysis(name='antelopev2', root='./', providers=['CUDAExecutionProvider', 'CPUExecutionProvider']) >>> app.prepare(ctx_id...
>>> from pipeline_stable_diffusion_xl_instantid import StableDiffusionXLInstantIDPipeline, draw_kps >>> # download 'antelopev2' under ./models >>> app = FaceAnalysis(name='antelopev2', root='./', providers=['CUDAExecutionProvider', 'CPUExecutionProvider']) ...