AttributeError: 'dict' object has no attribute 'shape' when use Noise Inversion

[zxwwxz001]

启用Noise Inversion的时候遇到错误AttributeError: 'dict' object has no attribute 'shape'

使用模型：animeArtDiffusionXL_alpha3.safetensors [53bb4fdc63] 插件为最新版（aa47321b） 具体错误信息如下 Traceback (most recent call last): File "/notebooks/sdwebui/stable-diffusion-webui/modules/call_queue.py", line 57, in f res = list(func(*args, kwargs)) File "/notebooks/sdwebui/stable-diffusion-webui/modules/call_queue.py", line 36, in f res = func(*args, *kwargs) File "/notebooks/sdwebui/stable-diffusion-webui/modules/img2img.py", line 208, in img2img processed = process_images(p) File "/notebooks/sdwebui/stable-diffusion-webui/modules/processing.py", line 732, in process_images res = process_images_inner(p) File "/notebooks/sdwebui/stable-diffusion-webui/modules/processing.py", line 867, in process_images_inner samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts) File "/notebooks/sdwebui/stable-diffusion-webui/modules/processing.py", line 1528, in sample samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning) File "/notebooks/sdwebui/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_utils/utils.py", line 246, in wrapper return fn(args, kwargs) File "/notebooks/sdwebui/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_utils/utils.py", line 246, in wrapper return fn(*args, kwargs) File "/notebooks/sdwebui/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/abstractdiffusion.py", line 652, in sample_img2img latent = self.find_noise_for_image_sigma_adjustment(sampler.model_wrap, self.noise_inverse_steps, prompts) File "/notebooks/sdwebui/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_utils/utils.py", line 246, in wrapper return fn(*args, *kwargs) File "/usr/local/lib/python3.9/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(args, kwargs) File "/notebooks/sdwebui/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/abstractdiffusion.py", line 729, in find_noise_for_image_sigma_adjustment eps = self.get_noise(x_in * c_in, t, cond_in, steps - i) File "/notebooks/sdwebui/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/multidiffusion.py", line 243, in get_noise return self.sample_one_step(x_in, org_func, repeat_func, custom_func) File "/notebooks/sdwebui/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/multidiffusion.py", line 165, in sample_one_step x_tile_out = repeat_func(x_tile, bboxes) File "/notebooks/sdwebui/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/multidiffusion.py", line 229, in repeat_func cond_out = self.repeat_cond_dict(cond_in_original, bboxes) File "/notebooks/sdwebui/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/multidiffusion.py", line 118, in repeat_cond_dict tcond = self.repeat_tensor(tcond, n_rep) File "/notebooks/sdwebui/stable-diffusion-webui/extensions/multidiffusion-upscaler-for-automatic1111/tile_methods/multidiffusion.py", line 103, in repeat_tensor B = x.shape[0] AttributeError: 'dict' object has no attribute 'shape'

[Kahsolt]

对SDXL的支持还需要更多兼容性测试，感谢错误报告~ 可能这个ckpt用到了某些暂未解析的 cond_dict 键，我先去下载来看看