getting stuck while generating using GPU

[noob-guy-dev]

i'm using v1.0.0-beta.15

on CPU its working perfectly, and while generating using set DEVICE = GPU , i was able to generate image 2-3 times .

But now i'm unable to generate using GPU , its getting stuck.

Command line output below:

Starting fastsdcpu... Python command check :OK Python version: 3.10.12 Running on Windows platform OS: Windows-10-10.0.22621-SP0 Processor: Intel64 Family 6 Model 154 Stepping 3, GenuineIntel Using device : GPU Found 7 stable diffusion models in config/stable-diffusion-models.txt Found 3 LCM-LoRA models in config/lcm-lora-models.txt Found 4 OpenVINO LCM models in config/openvino-lcm-models.txt Starting desktop GUI mode(Qt) Torch datatype : torch.float32 Output path : D:\fastsdcpu\results Reshape and compile {'guidance_scale': 1.0, 'image_height': 512, 'image_width': 512, 'inference_steps': 4, 'lcm_lora': {'base_model_id': 'Lykon/dreamshaper-8', 'lcm_lora_id': 'latent-consistency/lcm-lora-sdv1-5'}, 'lcm_model_id': 'rupeshs/LCM-dreamshaper-v7-openvino', 'negative_prompt': 'worst quality,low quality,normal quality,lowres,watermark', 'number_of_images': 1, 'openvino_lcm_model_id': 'rupeshs/LCM-dreamshaper-v7-openvino', 'prompt': 'best quality, masterpiece,1girl,white sweater', 'seed': -1, 'use_lcm_lora': False, 'use_offline_model': True, 'use_openvino': True, 'use_safety_checker': False, 'use_seed': False, 'use_tiny_auto_encoder': False} The config attributes {'algorithm_type': 'deis', 'lower_order_final': True, 'skip_prk_steps': True, 'solver_order': 2, 'solver_type': 'logrho', 'use_karras_sigmas': False} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file. D:\fastsdcpu\env\lib\site-packages\transformers\models\clip\feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead. warnings.warn( Compiling the vae_decoder to GPU ... Compiling the unet to GPU ... Compiling the text_encoder to GPU ... Compiling the vae_encoder to GPU ... Model :rupeshs/LCM-dreamshaper-v7-openvino Pipeline : OVStableDiffusionPipeline { "_class_name": "OVStableDiffusionPipeline", "_diffusers_version": "0.23.0", "_name_or_path": "rupeshs/LCM-dreamshaper-7", "feature_extractor": [ "transformers", "CLIPFeatureExtractor" ], "requires_safety_checker": true, "safety_checker": [ "stable_diffusion", "StableDiffusionSafetyChecker" ], "scheduler": [ "diffusers", "LCMScheduler" ], "text_encoder": [ "optimum", "OVModelTextEncoder" ], "text_encoder_2": [ null, null ], "tokenizer": [ "transformers", "CLIPTokenizer" ], "unet": [ "optimum", "OVModelUnet" ], "vae_decoder": [ "optimum", "OVModelVaeDecoder" ], "vae_encoder": [ "optimum", "OVModelVaeEncoder" ] }

The config attributes {'algorithm_type': 'deis', 'lower_order_final': True, 'skip_prk_steps': True, 'solver_order': 2, 'solver_type': 'logrho', 'use_karras_sigmas': False} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file. Using OpenVINO Reshape and compile Compiling the vae_decoder to GPU ... Compiling the unet to GPU ... Compiling the text_encoder to GPU ... Compiling the vae_encoder to GPU ... D:\fastsdcpu\env\lib\site-packages\optimum\intel\openvino\modeling_diffusion.py:565: FutureWarning: shared_memory is deprecated and will be removed in 2024.0. Value of shared_memory is going to override share_inputs value. Please use only share_inputs explicitly. outputs = self.request(inputs, shared_memory=True) 0%| | 0/4 [00:00<?, ?it/s]D:\fastsdcpu\env\lib\site-packages\optimum\intel\openvino\modeling_diffusion.py:599: FutureWarning: shared_memory is deprecated and will be removed in 2024.0. Value of shared_memory is going to override share_inputs value. Please use only share_inputs explicitly. outputs = self.request(inputs, shared_memory=True)

[rupeshs]

Which GPU?

[noob-guy-dev]

integrated Iris gpu

I'm using intel i5-12500H

[Disty0]

GPU has compile time. Wait for around a minute.

[rupeshs]

@noob-guy-dev As @Disty0 mentioned GPU has some compile time for the first time subsequent runs will be faster,

[noob-guy-dev]

@rupeshs , it's been 30 minutes... still stuck

[rupeshs]

@noob-guy-dev please try cpu or do a fresh install.

[noob-guy-dev]

i did reinstall, but same issue , looks like no gpu for me ,

CPU works without any issue.

still thank you for your time @rupeshs @Disty0

[rupeshs]

@noob-guy-dev Thanks for using FastSD CPU