unsure what im doing wrong using a 7900xtx / RuntimeError: shape '[1, 32, 1, 1, 1]' is invalid for input of size 0

[MackanJ2001]

[Tiled VAE]: input_size: torch.Size([1, 4, 144, 256]), tile_size: 128, padding: 11 [Tiled VAE]: split to 1x2 = 2 tiles. Optimal tile size 128x128, original tile size 128x128 [Tiled VAE]: Fast mode enabled, estimating group norm parameters on 128 x 72 image Error completing request Arguments: ('task(nuo70ibzjew1646)', 'technological advancement, futuristic,(character far back:1.5), 1girl, (large field of view:1.5), full body, holding sword, chinese dress,', 'badhandv4, easynegative,(worst quality, low quality:1.4), (depth of field, blurry:1.2), (greyscale, monochrome:1.1), 3D face, cropped, lowres, text, jpeg artifacts, signature, watermark, username, blurry, artist name, trademark, watermark, title, multiple view, Reference sheet,nsfw,, (worst quality, low quality:1.4), (depth of field, blurry:1.2), (greyscale, monochrome:1.1), 3D face, cropped, lowres, text, jpeg artifacts, signature, watermark, username, blurry, artist name, trademark, watermark, title, multiple view, Reference sheet,, longbody, lowres, bad anatomy, bad hands, missing fingers, pubic hair,extra digit, fewer digits, cropped, worst quality, low quality,( showing belly:1.5),', [], 20, 0, False, False, 30, 1, 7, -1.0, -1.0, 0, 0, 0, False, 1152, 2048, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, True, 'MultiDiffusion', False, 10, 1, 1, 64, True, True, 2048, 1152, 128, 128, 64, 1, 'None', 2, False, False, False, False, False, 0, 0, 1, 1, '', '', 'Background', 0.2, -1.0, False, 0, 0, 0.6, 0.6, '', '', 'Background', 0.2, -1.0, False, 0.4, 0, 0.6, 0.6, '', '', 'Background', 0.2, -1.0, False, 0, 0.4, 0.6, 0.6, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.6, 0.6, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, True, False, True, True, True, 1024, 128, False, False, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, 'Refresh models', False, False, 'none', 'None', 1, None, False, 'Scale to Fit (Inner Fit)', False, False, 64, 64, 64, 0, 1, False, False, False, False, False, '1:1,1:2,1:2', '0:0,0:0,0:1', '0.2,0.8,0.8', 20, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0, None, 50, 0, 1, 512, 512, True, False, False, True, True, False, 1, True, 3, False, 3, False, 3, 1) {} Traceback (most recent call last): File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f res = list(func(*args, **kwargs)) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f res = func(*args, **kwargs) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\modules\txt2img.py", line 56, in txt2img processed = process_images(p) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\modules\processing.py", line 503, in process_images res = process_images_inner(p) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\modules\processing.py", line 655, in process_images_inner x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))] File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\modules\processing.py", line 655, in x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))] File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\modules\processing.py", line 440, in decode_first_stage x = model.decode_first_stage(x) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 17, in setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs)) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 28, in call return self.__orig_func(*args, **kwargs) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage return self.first_stage_model.decode(z) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 90, in decode dec = self.decoder(z) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\extensions\multidiffusion-upscaler-for-automatic1111-main\scripts\vae_optimize.py", line 480, in call return self.vae_tile_forward(x) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\extensions\multidiffusion-upscaler-for-automatic1111-main\scripts\vae_optimize.py", line 362, in wrapper ret = fn(*args, **kwargs) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\extensions\multidiffusion-upscaler-for-automatic1111-main\scripts\vae_optimize.py", line 661, in vae_tile_forward if self.estimate_group_norm(downsampled_z, estimate_task_queue, color_fix=self.color_fix): File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\extensions\multidiffusion-upscaler-for-automatic1111-main\scripts\vae_optimize.py", line 575, in estimate_group_norm tile = group_norm_func(tile) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\extensions\multidiffusion-upscaler-for-automatic1111-main\scripts\vae_optimize.py", line 454, in group_norm_func return custom_group_norm(x, 32, mean, var, weight, bias, 1e-6) File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\extensions\multidiffusion-upscaler-for-automatic1111-main\scripts\vae_optimize.py", line 324, in custom_group_norm out = F.batch_norm(input_reshaped, mean, var, weight=None, bias=None, File "B:\applicationer\diffusion\automatic1111\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\functional.py", line 2450, in batch_norm return torch.batch_norm( RuntimeError: shape '[1, 32, 1, 1, 1]' is invalid for input of size 0

Im also sometimes getting the could not allocate tenso with "xxxx" bytes. there is not enough gpu video memory specs is 7900xtx 24gb vram 3900x 32gb ram "edit using windows 10"

[sorryhorizonTT]

seems like it appears only between amd users. i have this error also "RuntimeError: shape '[1, 32, 1, 1, 1]' is invalid for input of size 0" im 6700xt user btw kick me if there is any solution

[wzddl]

kick me if there is any solution 我也同样有这个问题，有解决方案记得踢我

[SGKino]

Same issue here, using the RTX 4070. "RuntimeError: shape '[2, 64, 96, 320]' is invalid for input of size 5898240"

I only got this error, when I am using some anime model like "Ghost", in img2img upscaling.

Update: I somehow solve the issue, if I choose the latent mode(my original image is generated with regional prompter) when upscaling. Hope this may help you guys in debug.