unsupported embed per head

[CaptnSeraph]

*** Error completing request
*** Arguments: ('task(v72wf3zvi5qfi74)', 'prompt', [], 30, 9, False, False, 1, 2, 4, -1.0, -1.0, 0, 0, 0, False, 832, 480, False, 0.7, 2, 'Latent', 0, 0, 0, 0, '', '', [], 0, False, {'ad_model': 'face_yolov8n.pt', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 32, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'inpaint_global_harmonious', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1}, {'ad_model': 'None', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 32, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'inpaint_global_harmonious', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1}, False, 'MultiDiffusion', False, True, 1024, 1024, 96, 96, 48, 1, 'None', 2, False, 10, 1, 1, 64, False, False, False, False, 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, 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, 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, 2048, 128, True, True, True, False, True, False, 1, False, False, False, 1.1, 1.5, 100, 0.7, False, False, True, False, False, 0, 'Gustavosta/MagicPrompt-Stable-Diffusion', '', False, 7, 100, 'Constant', 0, 'Constant', 0, 4, False, 'x264', 'blend', 10, 0, 0, False, True, True, True, 'intermediate', 'animation', False, False, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, None, 'Refresh models', <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x000002032947B010>, <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x0000020329626770>, <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x000002032940E350>, <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x000002032947B820>, [], [<PIL.Image.Image image mode=RGB size=480x832 at 0x203279B7C40>], False, 4, 0, 0.8, 0, 0.8, 0.5, False, False, False, 'Matrix', 'Horizontal', 'Mask', 'Prompt', '1,1', '0.2', False, False, False, 'Attention', False, '0', '0', '0.4', None, None, False, '0', 'I:\\stable-diffusion-webui\\models\\roop\\inswapper_128.onnx', 'CodeFormer', 1, '', 1, 1, False, True, False, False, 0, None, [], 0, False, [], [], False, 0, 1, False, False, 0, None, [], -2, False, [], False, 0, None, None, 1, False, False, False, False, False, False, False, False, '1:1,1:2,1:2', '0:0,0:0,0:1', '0.2,0.8,0.8', 150, 0.2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 150, True, False, False, 'positive', 'comma', 0, False, False, '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, 8, True, True, 16, 'PNN', True, None, None, False, None, None, False, None, None, False, None, None, False, 50) {}
    Traceback (most recent call last):
      File "I:\stable-diffusion-webui\modules\call_queue.py", line 55, in f
        res = list(func(*args, **kwargs))
      File "I:\stable-diffusion-webui\modules\call_queue.py", line 35, in f
        res = func(*args, **kwargs)
      File "I:\stable-diffusion-webui\modules\txt2img.py", line 57, in txt2img
        processed = processing.process_images(p)
      File "I:\stable-diffusion-webui\modules\processing.py", line 620, in process_images
        res = process_images_inner(p)
      File "I:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 42, in processing_process_images_hijack
        return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
      File "I:\stable-diffusion-webui\modules\processing.py", line 739, 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 "I:\stable-diffusion-webui\extensions\sd-webui-fabric\scripts\marking.py", line 28, in process_sample
        return process.sample_before_CN_hack(*args, **kwargs)
      File "I:\stable-diffusion-webui\modules\processing.py", line 992, in sample
        samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
      File "I:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 439, in sample
        samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
      File "I:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 278, in launch_sampling
        return func()
      File "I:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 439, in <lambda>
        samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
      File "I:\stable-diffusion-webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
        return func(*args, **kwargs)
      File "I:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\sampling.py", line 225, in sample_dpm_2_ancestral
        denoised = model(x, sigmas[i] * s_in, **extra_args)
      File "I:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "I:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 158, in forward
        x_out = self.inner_model(x_in, sigma_in, cond=make_condition_dict([cond_in], image_cond_in))
      File "I:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "I:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\external.py", line 112, in forward
        eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
      File "I:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\external.py", line 138, in get_eps
        return self.inner_model.apply_model(*args, **kwargs)
      File "I:\stable-diffusion-webui\modules\sd_hijack_utils.py", line 17, in <lambda>
        setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
      File "I:\stable-diffusion-webui\modules\sd_hijack_utils.py", line 28, in __call__
        return self.__orig_func(*args, **kwargs)
      File "I:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 858, in apply_model
        x_recon = self.model(x_noisy, t, **cond)
      File "I:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "I:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 1335, in forward
        out = self.diffusion_model(x, t, context=cc)
      File "I:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "I:\stable-diffusion-webui\extensions\sd-webui-fabric\scripts\patching.py", line 187, in new_forward
        out = self._fabric_old_forward(x, timesteps, context, **kwargs)
      File "I:\stable-diffusion-webui\modules\sd_unet.py", line 91, in UNetModel_forward
        return ldm.modules.diffusionmodules.openaimodel.copy_of_UNetModel_forward_for_webui(self, x, timesteps, context, *args, **kwargs)
      File "I:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\openaimodel.py", line 797, in forward
        h = module(h, emb, context)
      File "I:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "I:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\openaimodel.py", line 84, in forward
        x = layer(x, context)
      File "I:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "I:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\attention.py", line 334, in forward
        x = block(x, context=context[i])
      File "I:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "I:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\attention.py", line 269, in forward
        return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)
      File "I:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\util.py", line 121, in checkpoint
        return CheckpointFunction.apply(func, len(inputs), *args)
      File "I:\stable-diffusion-webui\venv\lib\site-packages\torch\autograd\function.py", line 506, in apply
        return super().apply(*args, **kwargs)  # type: ignore[misc]
      File "I:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\util.py", line 136, in forward
        output_tensors = ctx.run_function(*ctx.input_tensors)
      File "I:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\attention.py", line 272, in _forward
        x = self.attn1(self.norm1(x), context=context if self.disable_self_attn else None) + x
      File "I:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "I:\stable-diffusion-webui\extensions\sd-webui-fabric\scripts\patching.py", line 168, in patched_attn1_forward
        out_cond = weighted_attention(attn1, attn1._fabric_old_forward, x_cond, ctx_cond, ws, **kwargs)  # (n_cond, seq, dim)
      File "I:\stable-diffusion-webui\extensions\sd-webui-fabric\scripts\weighted_attention.py", line 153, in weighted_attention
        out = attn_fn(x, context=context, **kwargs)
      File "I:\stable-diffusion-webui\modules\sd_hijack_optimizations.py", line 461, in xformers_attention_forward
        out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None, op=get_xformers_flash_attention_op(q, k, v))
      File "I:\stable-diffusion-webui\extensions\sd-webui-fabric\scripts\weighted_attention.py", line 47, in patched_xformers_attn
        return orig_attn(q, k, v, attn_bias=attn_bias, op=op)
      File "I:\stable-diffusion-webui\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 196, in memory_efficient_attention
        return _memory_efficient_attention(
      File "I:\stable-diffusion-webui\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 294, in _memory_efficient_attention
        return _memory_efficient_attention_forward(
      File "I:\stable-diffusion-webui\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 310, in _memory_efficient_attention_forward
        op = _dispatch_fw(inp)
      File "I:\stable-diffusion-webui\venv\lib\site-packages\xformers\ops\fmha\dispatch.py", line 98, in _dispatch_fw
        return _run_priority_list(
      File "I:\stable-diffusion-webui\venv\lib\site-packages\xformers\ops\fmha\dispatch.py", line 73, in _run_priority_list
        raise NotImplementedError(msg)
    NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:
         query       : shape=(2, 390, 8, 160) (torch.float16)
         key         : shape=(2, 390, 8, 160) (torch.float16)
         value       : shape=(2, 390, 8, 160) (torch.float16)
         attn_bias   : <class 'torch.Tensor'>
         p           : 0.0
    `cutlassF` is not supported because:
        attn_bias.stride(-2) % 8 != 0 (attn_bias.stride() = (1216800, 152100, 390, 1))
        attn_bias.stride(-2) % 8 != 0 (attn_bias.stride() = (1216800, 152100, 390, 1))
        HINT: To use an `attn_bias` with a sequence length that is not a multiple of 8, you need to ensure memory is aligned by slicing a bigger tensor. Example: use `attn_bias = torch.zeros([1, 1, 5, 8])[:,:,:,:5]` instead of `torch.zeros([1, 1, 5, 5])`
    `flshattF` is not supported because:
        max(query.shape[-1] != value.shape[-1]) > 128
        attn_bias type is <class 'torch.Tensor'>
    `tritonflashattF` is not supported because:
        max(query.shape[-1] != value.shape[-1]) > 128
        attn_bias type is <class 'torch.Tensor'>
        triton is not available
        requires A100 GPU
    `smallkF` is not supported because:
        dtype=torch.float16 (supported: {torch.float32})
        max(query.shape[-1] != value.shape[-1]) > 32
        bias with non-zero stride not supported
        unsupported embed per head: 160

[dvruette]

Seems like an issue with xformers, so as a trmporary workaround please try using a different attention processor.

[CaptnSeraph]

it does seem to work without xformers so, theres that

[CaptnSeraph]

ok, does not work with xformers, works with --sdp-opt-attention, does not work with --medvram as it gives a tensors on multiple device error.

[dvruette]

Going to keep this open for now, there still seems to be some stuff not working quite right.

[dvruette]

I've tested the settings you mentioned and they're working for me: --xformers, --medvram and --xformers --medvram

I'd expect the settings to work in general on the newest version, so feel free to reopen if you run into problems again.