[bug]: Could not generate image

[GihanAbenayake]

Is there an existing issue for this?

• [X] I have searched the existing issues

OS

Windows

GPU

cuda

VRAM

4GB

What version did you experience this issue on?

2.3.2

What happened?

Opened Invoke with Web based Browser Typed in: Anime Girl with Green hair and Red eyes into Text to Image prompt Set width and Height to 320 x 320 Steps to 50 Invoke

Screenshots

Traceback (most recent call last): File "D:\InvokeAI.venv\lib\site-packages\ldm\generate.py", line 559, in prompt2image results = generator.generate( File "D:\InvokeAI.venv\lib\site-packages\ldm\invoke\generator\base.py", line 115, in generate image = make_image(x_T) File "D:\InvokeAI.venv\lib\site-packages\ldm\invoke\generator\txt2img.py", line 45, in make_image pipeline_output = pipeline.image_from_embeddings( File "D:\InvokeAI.venv\lib\site-packages\ldm\invoke\generator\diffusers_pipeline.py", line 419, in image_from_embeddings result_latents, result_attention_map_saver = self.latents_from_embeddings( File "D:\InvokeAI.venv\lib\site-packages\ldm\invoke\generator\diffusers_pipeline.py", line 445, in latents_from_embeddings result: PipelineIntermediateState = infer_latents_from_embeddings( File "D:\InvokeAI.venv\lib\site-packages\ldm\invoke\generator\diffusers_pipeline.py", line 178, in call for result in self.generator_method(*args, kwargs): File "D:\InvokeAI.venv\lib\site-packages\ldm\invoke\generator\diffusers_pipeline.py", line 481, in generate_latents_from_embeddings step_output = self.step(batched_t, latents, conditioning_data, File "D:\InvokeAI.venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context return func(*args, *kwargs) File "D:\InvokeAI.venv\lib\site-packages\ldm\invoke\generator\diffusers_pipeline.py", line 525, in step noise_pred = self.invokeai_diffuser.do_diffusion_step( File "D:\InvokeAI.venv\lib\site-packages\ldm\models\diffusion\shared_invokeai_diffusion.py", line 166, in do_diffusion_step unconditioned_next_x, conditioned_next_x = self._apply_standard_conditioning( File "D:\InvokeAI.venv\lib\site-packages\ldm\models\diffusion\shared_invokeai_diffusion.py", line 207, in _apply_standard_conditioning both_results = self.model_forward_callback(x_twice, sigma_twice, both_conditionings) File "D:\InvokeAI.venv\lib\site-packages\ldm\invoke\generator\diffusers_pipeline.py", line 559, in _unet_forward return self.unet(latents, t, text_embeddings, File "D:\InvokeAI.venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(input, kwargs) File "D:\InvokeAI.venv\lib\site-packages\diffusers\models\unet_2d_condition.py", line 582, in forward sample, res_samples = downsample_block( File "D:\InvokeAI.venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, kwargs) File "D:\InvokeAI.venv\lib\site-packages\diffusers\models\unet_2d_blocks.py", line 837, in forward hidden_states = attn( File "D:\InvokeAI.venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, *kwargs) File "D:\InvokeAI.venv\lib\site-packages\diffusers\models\transformer_2d.py", line 265, in forward hidden_states = block( File "D:\InvokeAI.venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(input, kwargs) File "D:\InvokeAI.venv\lib\site-packages\diffusers\models\attention.py", line 291, in forward attn_output = self.attn1( File "D:\InvokeAI.venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) File "D:\InvokeAI.venv\lib\site-packages\diffusers\models\cross_attention.py", line 205, in forward return self.processor( File "D:\InvokeAI.venv\lib\site-packages\diffusers\models\cross_attention.py", line 456, in call hidden_states = xformers.ops.memory_efficient_attention( File "D:\InvokeAI.venv\lib\site-packages\xformers\ops\fmha__init.py", line 197, in memory_efficient_attention return _memory_efficient_attention( File "D:\InvokeAI.venv\lib\site-packages\xformers\ops\fmha__init__.py", line 293, in _memory_efficient_attention return _memory_efficient_attention_forward( File "D:\InvokeAI.venv\lib\site-packages\xformers\ops\fmha\init__.py", line 309, in _memory_efficient_attention_forward op = _dispatch_fw(inp) File "D:\InvokeAI.venv\lib\site-packages\xformers\ops\fmha\dispatch.py", line 95, in _dispatch_fw return _run_priority_list( File "D:\InvokeAI.venv\lib\site-packages\xformers\ops\fmha\dispatch.py", line 70, in _run_priority_list raise NotImplementedError(msg) NotImplementedError: No operator found for memory_efficient_attention_forward with inputs: query : shape=(10, 1600, 1, 64) (torch.float32) key : shape=(10, 1600, 1, 64) (torch.float32) value : shape=(10, 1600, 1, 64) (torch.float32) attn_bias : <class 'NoneType'> p : 0.0 cutlassF is not supported because: device=cpu (supported: {'cuda'}) flshattF is not supported because: device=cpu (supported: {'cuda'}) dtype=torch.float32 (supported: {torch.float16, torch.bfloat16}) tritonflashattF is not supported because: device=cpu (supported: {'cuda'}) dtype=torch.float32 (supported: {torch.float16, torch.bfloat16}) triton is not available smallkF is not supported because: max(query.shape[-1] != value.shape[-1]) > 32 unsupported embed per head: 64 >> Could not generate image.

Additional context

No response

Contact Details

No response

[GihanAbenayake]

Waifu Diffusion 1.4 FYI

[hipsterusername]

Your installation doesn’t appear to be using your gpu. There’s a reference to device being “cpu”.

You might consider reinstalling

[gy2256]

Same issue here. It's not using GPU.