vladmandic / automatic

SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models
https://github.com/vladmandic/automatic
GNU Affero General Public License v3.0
5.67k stars 419 forks source link

[Issue]: [AMD] "HIP error: no kernel image is available for execution on the device" #3525

Open noversi117 opened 4 days ago

noversi117 commented 4 days ago

Issue Description

Before updating to the current version, everything was working fine. Until I ran the "upgrade" command. Now not even a fresh install fixes this error. It loads up fine, but will not load any model nor generate anything because of this error. Nothing else has changed on my system.

Linux Mint 6.2.7 Kernel 6.8.0-38-generic AMD 7900 XTX

Here is everything from the debug log.

Version Platform Description

No response

Relevant log output

21:09:05-058317 INFO     Starting SD.Next                                       
21:09:05-061085 INFO     Logger: file="/home/noversi/Desktop/Image              
                         Generators/automatic/sdnext.log" level=DEBUG size=64   
                         mode=create                                            
21:09:05-062110 INFO     Python: version=3.10.14 platform=Linux                 
                         bin="/home/noversi/Desktop/Image                       
                         Generators/automatic/venv/bin/python3"                 
                         venv="/home/noversi/Desktop/Image                      
                         Generators/automatic/venv"                             
21:09:05-069841 INFO     Version: app=sd.next updated=2024-10-24 hash=06dd9e5f  
                         branch=master                                          
                         url=https://github.com/vladmandic/automatic/tree/master
                         ui=main                                                
21:09:05-392068 INFO     Platform: arch=x86_64 cpu=x86_64 system=Linux          
                         release=6.8.0-38-generic python=3.10.14                
21:09:05-397800 DEBUG    Setting environment tuning                             
21:09:05-406866 DEBUG    Torch allocator:                                       
                         "garbage_collection_threshold:0.80,max_split_size_mb:51
                         2"                                                     
21:09:05-438283 DEBUG    Torch overrides: cuda=False rocm=False ipex=False      
                         directml=False openvino=False zluda=False              
21:09:05-439792 INFO     Python: version=3.10.14 platform=Linux                 
                         bin="/home/noversi/Desktop/Image                       
                         Generators/automatic/venv/bin/python3"                 
                         venv="/home/noversi/Desktop/Image                      
                         Generators/automatic/venv"                             
21:09:05-440904 INFO     ROCm: AMD toolkit detected                             
21:09:05-466808 INFO     ROCm: agents=['gfx1100']                               
21:09:05-467959 INFO     ROCm: version=6.2, using agent gfx1100                 
21:09:05-506582 INFO     Verifying requirements                                 
21:09:05-511231 INFO     Verifying packages                                     
21:09:05-514421 DEBUG    Timestamp repository update time: Thu Oct 24 19:48:38  
                         2024                                                   
21:09:05-515359 INFO     Startup: standard                                      
21:09:05-516073 INFO     Verifying submodules                                   
21:09:05-716154 DEBUG    Git submodule: extensions-builtin/sd-extension-chainner
                         / main                                                 
21:09:05-742079 DEBUG    Git submodule:                                         
                         extensions-builtin/sd-extension-system-info / main     
21:09:05-766585 DEBUG    Git submodule:                                         
                         extensions-builtin/sd-webui-agent-scheduler / main     
21:09:05-801137 DEBUG    Git detached head detected:                            
                         folder="extensions-builtin/sdnext-modernui"            
                         reattach=main                                          
21:09:05-805866 DEBUG    Git submodule: extensions-builtin/sdnext-modernui /    
                         main                                                   
21:09:05-833456 DEBUG    Git submodule:                                         
                         extensions-builtin/stable-diffusion-webui-rembg /      
                         master                                                 
21:09:05-854979 DEBUG    Git submodule: modules/k-diffusion / master            
21:09:05-880683 DEBUG    Git submodule: wiki / master                           
21:09:05-896848 DEBUG    Register paths                                         
21:09:05-947405 DEBUG    Installed packages: 181                                
21:09:05-948414 DEBUG    Extensions all: ['sd-extension-chainner',              
                         'sd-extension-system-info', 'sdnext-modernui',         
                         'stable-diffusion-webui-rembg', 'Lora',                
                         'sd-webui-agent-scheduler']                            
21:09:06-009145 DEBUG    Extension installer: /home/noversi/Desktop/Image       
                         Generators/automatic/extensions-builtin/stable-diffusio
                         n-webui-rembg/install.py                               
21:09:12-084553 DEBUG    Extension installer: /home/noversi/Desktop/Image       
                         Generators/automatic/extensions-builtin/sd-webui-agent-
                         scheduler/install.py                                   
21:09:13-934320 DEBUG    Extensions all: []                                     
21:09:13-935281 INFO     Extensions enabled: ['sd-extension-chainner',          
                         'sd-extension-system-info', 'sdnext-modernui',         
                         'stable-diffusion-webui-rembg', 'Lora',                
                         'sd-webui-agent-scheduler']                            
21:09:13-936294 INFO     Verifying requirements                                 
21:09:13-937118 DEBUG    Setup complete without errors: 1729991354              
21:09:13-938782 DEBUG    Extension preload: {'extensions-builtin': 0.0,         
                         'extensions': 0.0}                                     
21:09:13-939946 DEBUG    Starting module: <module 'webui' from                  
                         '/home/noversi/Desktop/Image                           
                         Generators/automatic/webui.py'>                        
21:09:13-941440 INFO     Command line args: ['--debug'] debug=True              
21:09:13-942868 DEBUG    Env flags: []                                          
21:09:17-803724 DEBUG    System: cores=16 affinity=16 threads=8                 
21:09:17-807205 INFO     System packages: {'torch': '2.4.1+rocm6.1',            
                         'diffusers': '0.32.0.dev0', 'gradio': '3.43.2',        
                         'transformers': '4.45.2', 'accelerate': '1.0.0'}       
21:09:18-243444 DEBUG    Huggingface cache:                                     
                         folder="/home/noversi/.cache/huggingface/hub"          
21:09:18-248602 INFO     Device detect: memory=24.0 optimization=none           
21:09:18-250030 DEBUG    Read: file="config.json" json=24 bytes=1091 time=0.000 
21:09:18-251340 INFO     Engine: backend=Backend.DIFFUSERS compute=rocm         
                         device=cuda attention="Scaled-Dot-Product" mode=no_grad
21:09:18-252489 DEBUG    Read: file="html/reference.json" json=58 bytes=30594   
                         time=0.000                                             
21:09:18-499054 WARNING  Torch FP16 test fail: HIP error: no kernel image is    
                         available for execution on the device                  
                         HIP kernel errors might be asynchronously reported at  
                         some other API call, so the stacktrace below might be  
                         incorrect.                                             
                         For debugging consider passing AMD_SERIALIZE_KERNEL=3  
                         Compile with `TORCH_USE_HIP_DSA` to enable device-side 
                         assertions.                                            

21:09:18-503244 WARNING  Torch BF16 test fail: HIP error: no kernel image is    
                         available for execution on the device                  
                         HIP kernel errors might be asynchronously reported at  
                         some other API call, so the stacktrace below might be  
                         incorrect.                                             
                         For debugging consider passing AMD_SERIALIZE_KERNEL=3  
                         Compile with `TORCH_USE_HIP_DSA` to enable device-side 
                         assertions.                                            

21:09:18-505838 INFO     Torch parameters: backend=rocm device=cuda config=Auto 
                         dtype=torch.float32 vae=torch.float32                  
                         unet=torch.float32 context=no_grad nohalf=False        
                         nohalfvae=False upscast=False deterministic=False      
                         test-fp16=False test-bf16=False                        
                         optimization="Scaled-Dot-Product"                      
21:09:18-735475 DEBUG    ONNX: version=1.19.2 provider=ROCMExecutionProvider,   
                         available=['AzureExecutionProvider',                   
                         'CPUExecutionProvider']                                
21:09:18-779000 INFO     Device: device=Radeon RX 7900 XTX n=1                  
                         hip=6.1.40091-a8dbc0c19                                
21:09:18-857851 DEBUG    Importing LDM                                          
21:09:18-863174 DEBUG    Entering start sequence                                
21:09:18-864882 DEBUG    Initializing                                           
21:09:18-886585 INFO     Available VAEs: path="models/VAE" items=0              
21:09:18-888318 INFO     Available UNets: path="models/UNET" items=0            
21:09:18-889739 INFO     Available TEs: path="models/Text-encoder" items=0      
21:09:18-891157 INFO     Disabled extensions: ['sdnext-modernui']               
21:09:18-892818 DEBUG    Read: file="cache.json" json=1 bytes=189 time=0.000    
21:09:18-894583 DEBUG    Read: file="metadata.json" json=1 bytes=1291 time=0.000
21:09:18-896225 DEBUG    Scanning diffusers cache: folder="models/Diffusers"    
                         items=0 time=0.00                                      
21:09:18-897712 INFO     Available Models: path="models/Stable-diffusion"       
                         items=1 time=0.01                                      
21:09:18-933221 INFO     Available Yolo: path="models/yolo" items=6 downloaded=0
21:09:18-934492 DEBUG    Load extensions                                        
21:09:18-984872 INFO     Available LoRAs: items=0 folders=2                     
21:09:19-445710 INFO     Extension:                                             
                         script='extensions-builtin/sd-webui-agent-scheduler/scr
                         ipts/task_scheduler.py' Using sqlite file:             
                         extensions-builtin/sd-webui-agent-scheduler/task_schedu
                         ler.sqlite3                                            
21:09:19-448611 DEBUG    Extensions init time: 0.51 Lora=0.17                   
                         sd-webui-agent-scheduler=0.27                          
21:09:19-463975 DEBUG    Read: file="html/upscalers.json" json=4 bytes=2640     
                         time=0.008                                             
21:09:19-651272 DEBUG    Read:                                                  
                         file="extensions-builtin/sd-extension-chainner/models.j
                         son" json=24 bytes=2693 time=0.000                     
21:09:19-654144 DEBUG    chaiNNer models: path="models/chaiNNer" defined=24     
                         discovered=0 downloaded=0                              
21:09:19-657086 INFO     Available Upscalers: items=53 downloaded=0 user=0      
                         time=0.21 types=['None', 'Lanczos', 'Nearest',         
                         'ChaiNNer', 'RealESRGAN', 'SwinIR', 'SCUNet', 'LDSR',  
                         'ESRGAN', 'SD', 'AuraSR']                              
21:09:19-676484 INFO     Available Styles: folder="models/styles" items=288     
                         time=0.02                                              
21:09:19-679230 DEBUG    Creating UI                                            
21:09:19-680468 DEBUG    UI themes available: type=Standard themes=12           
21:09:19-681674 INFO     UI theme: type=Standard name="black-teal"              
21:09:19-684232 DEBUG    UI theme: css="/home/noversi/Desktop/Image             
                         Generators/automatic/javascript/black-teal.css"        
                         base="sdnext.css" user="None"                          
21:09:19-686733 DEBUG    UI initialize: txt2img                                 
21:09:19-714252 DEBUG    Networks: page='model' items=58 subfolders=2           
                         tab=txt2img folders=['models/Stable-diffusion',        
                         'models/Diffusers', 'models/Reference'] list=0.01      
                         thumb=0.00 desc=0.00 info=0.00 workers=8 sort=Default  
21:09:19-716528 DEBUG    Networks: page='lora' items=0 subfolders=0 tab=txt2img 
                         folders=['models/Lora', 'models/LyCORIS'] list=0.00    
                         thumb=0.00 desc=0.00 info=0.00 workers=8 sort=Default  
21:09:19-725846 DEBUG    Networks: page='style' items=288 subfolders=1          
                         tab=txt2img folders=['models/styles', 'html'] list=0.01
                         thumb=0.00 desc=0.00 info=0.00 workers=8 sort=Default  
21:09:19-729375 DEBUG    Networks: page='embedding' items=0 subfolders=0        
                         tab=txt2img folders=['models/embeddings'] list=0.00    
                         thumb=0.00 desc=0.00 info=0.00 workers=8 sort=Default  
21:09:19-731651 DEBUG    Networks: page='vae' items=0 subfolders=0 tab=txt2img  
                         folders=['models/VAE'] list=0.00 thumb=0.00 desc=0.00  
                         info=0.00 workers=8 sort=Default                       
21:09:19-733430 DEBUG    Networks: page='history' items=0 subfolders=0          
                         tab=txt2img folders=[] list=0.00 thumb=0.00 desc=0.00  
                         info=0.00 workers=8 sort=Default                       
21:09:19-860329 DEBUG    UI initialize: img2img                                 
21:09:20-015075 DEBUG    UI initialize: control models=models/control           
21:09:20-446362 DEBUG    Read: file="ui-config.json" json=0 bytes=2 time=0.000  
21:09:20-603578 DEBUG    UI themes available: type=Standard themes=12           
21:09:20-782650 DEBUG    Reading failed: /home/noversi/Desktop/Image            
                         Generators/automatic/html/extensions.json [Errno 2] No 
                         such file or directory: '/home/noversi/Desktop/Image   
                         Generators/automatic/html/extensions.json'             
21:09:20-783780 INFO     Extension list is empty: refresh required              
21:09:20-809562 DEBUG    Extension list: processed=6 installed=6 enabled=5      
                         disabled=1 visible=6 hidden=0                          
21:09:21-215264 DEBUG    Root paths: ['/home/noversi/Desktop/Image              
                         Generators/automatic']                                 
21:09:21-303856 INFO     Local URL: http://127.0.0.1:7860/                      
21:09:21-304892 DEBUG    Gradio functions: registered=1894                      
21:09:21-306103 DEBUG    FastAPI middleware: ['Middleware', 'Middleware']       
21:09:21-309731 DEBUG    Creating API                                           
21:09:21-533569 INFO     [AgentScheduler] Task queue is empty                   
21:09:21-535225 INFO     [AgentScheduler] Registering APIs                      
21:09:21-678035 DEBUG    Scripts setup: ['IP Adapters:0.037', 'XYZ Grid:0.035', 
                         'Face:0.019', 'AnimateDiff:0.01', 'CogVideoX:0.011',   
                         'Ctrl-X:0.009', 'HDR:0.006', 'LUT Color grading:0.008',
                         'Prompt enhance:0.005', 'Text-to-Video:0.005',         
                         'Image-to-Video:0.009', 'Stable Video Diffusion:0.007']
21:09:21-679363 DEBUG    Model metadata: file="metadata.json" no changes        
21:09:21-680098 DEBUG    Model auto load disabled                               
21:09:21-681103 DEBUG    Script callback init time:                             
                         system-info.py:app_started=0.07                        
                         task_scheduler.py:app_started=0.17                     
21:09:21-682041 INFO     Startup time: 7.73 torch=3.08 gradio=0.62              
                         diffusers=0.07 libraries=1.13 extensions=0.51          
                         upscalers=0.21 ui-networks=0.19 ui-txt2img=0.11        
                         ui-img2img=0.11 ui-control=0.20 ui-extras=0.06         
                         ui-models=0.05 ui-settings=0.33 ui-extensions=0.07     
                         ui-defaults=0.32 launch=0.16 api=0.13 app-started=0.24 
21:09:21-685286 DEBUG    Save: file="config.json" json=24 bytes=1091 time=0.004 
21:09:59-726869 DEBUG    Server: alive=True jobs=0 requests=8 uptime=42         
                         memory=1.44/31.2 backend=Backend.DIFFUSERS state=idle  
21:10:40-166865 DEBUG    UI themes available: type=Standard themes=12           
21:10:42-901565 INFO     Browser session: user=None client=127.0.0.1            
                         agent=Mozilla/5.0 (X11; Linux x86_64; rv:128.0)        
                         Gecko/20100101 Firefox/128.0                           
21:10:43-247539 INFO     MOTD: N/A                                              
21:10:51-870556 DEBUG    Model requested: fn=f:txt2img                          
21:10:51-871910 INFO     Load model: select="talesOfDigitalLife_v131            
                         [b24a67fa46]"                                          
21:10:51-874985 INFO     Autodetect model: detect="Stable Diffusion XL"         
                         class=StableDiffusionXLPipeline                        
                         file="/home/noversi/Desktop/Image                      
                         Generators/automatic/models/Stable-diffusion/talesOfDig
                         italLife_v131.safetensors" size=6617MB                 
Diffusers  2.96it/s ████████ 100% 7/7 00:02 00:00 Loading pipeline components...
21:10:54-512560 DEBUG    Setting model: pipeline=StableDiffusionXLPipeline      
                         config={'low_cpu_mem_usage': True, 'torch_dtype':      
                         torch.float32, 'load_connected_pipeline': True,        
                         'extract_ema': False, 'config': 'configs/sdxl',        
                         'use_safetensors': True, 'cache_dir':                  
                         '/home/noversi/.cache/huggingface/hub'}                
21:10:54-515167 INFO     Load network: type=embeddings loaded=0 skipped=0       
                         time=0.00                                              
21:10:54-516279 DEBUG    Setting model: component=VAE slicing=True              
21:10:54-517327 DEBUG    Setting model: attention="Scaled-Dot-Product"          
21:10:54-543151 DEBUG    Setting model: offload=none                            
21:10:54-544935 DEBUG    Read: file="/home/noversi/Desktop/Image                
                         Generators/automatic/configs/sdxl/vae/config.json"     
                         json=15 bytes=642 time=0.000                           
21:10:56-881213 DEBUG    GC: utilization={'gpu': 57, 'ram': 33, 'threshold': 80}
                         gc={'collected': 424, 'saved': 0.0} before={'gpu':     
                         13.57, 'ram': 10.32} after={'gpu': 13.57, 'ram': 10.32,
                         'retries': 0, 'oom': 0} device=cuda                    
                         fn=reload_model_weights:load_diffuser time=0.27        
21:10:56-895331 INFO     Load model: time=4.73 load=2.64 move=2.06 native=1024  
                         memory={'ram': {'used': 10.32, 'total': 31.2}, 'gpu':  
                         {'used': 13.57, 'total': 23.98}, 'retries': 0, 'oom':  
                         0}                                                     
21:10:56-924776 INFO     Base: class=StableDiffusionXLPipeline                  
21:10:56-926701 DEBUG    Sampler: sampler=default class=EulerDiscreteScheduler: 
                         {'num_train_timesteps': 1000, 'beta_start': 0.00085,   
                         'beta_end': 0.012, 'beta_schedule': 'scaled_linear',   
                         'trained_betas': None, 'prediction_type': 'epsilon',   
                         'interpolation_type': 'linear', 'use_karras_sigmas':   
                         False, 'use_exponential_sigmas': False,                
                         'use_beta_sigmas': False, 'sigma_min': None,           
                         'sigma_max': None, 'timestep_spacing': 'leading',      
                         'timestep_type': 'discrete', 'steps_offset': 1,        
                         'rescale_betas_zero_snr': False, 'final_sigmas_type':  
                         'zero', 'clip_sample': False, 'sample_max_value': 1.0, 
                         'set_alpha_to_one': False, 'skip_prk_steps': True}     
21:10:56-933036 ERROR    Prompt parser encode: HIP error: no kernel image is    
                         available for execution on the device                  
                         HIP kernel errors might be asynchronously reported at  
                         some other API call, so the stacktrace below might be  
                         incorrect.                                             
                         For debugging consider passing AMD_SERIALIZE_KERNEL=3  
                         Compile with `TORCH_USE_HIP_DSA` to enable device-side 
                         assertions.                                            

21:10:56-937598 DEBUG    Torch generator: device=cuda seeds=[2399070899]        
21:10:56-938800 DEBUG    Diffuser pipeline: StableDiffusionXLPipeline           
                         task=DiffusersTaskType.TEXT_2_IMAGE batch=1/1x1        
                         set={'prompt': 1, 'negative_prompt': 1,                
                         'guidance_scale': 6, 'num_inference_steps': 20, 'eta': 
                         1.0, 'guidance_rescale': 0.7, 'denoising_end': None,   
                         'output_type': 'latent', 'width': 1024, 'height': 1024,
                         'parser': 'Fixed attention'}                           
21:10:56-953370 ERROR    Processing: step=base args={'prompt': ['test'],        
                         'negative_prompt': [''], 'guidance_scale': 6,          
                         'generator': [<torch._C.Generator object at            
                         0x7819f65e9850>], 'callback_on_step_end': <function    
                         diffusers_callback at 0x781863dbbf40>,                 
                         'callback_on_step_end_tensor_inputs': ['latents',      
                         'prompt_embeds', 'negative_prompt_embeds',             
                         'add_text_embeds', 'add_time_ids',                     
                         'negative_pooled_prompt_embeds',                       
                         'negative_add_time_ids'], 'num_inference_steps': 20,   
                         'eta': 1.0, 'guidance_rescale': 0.7, 'denoising_end':  
                         None, 'output_type': 'latent', 'width': 1024, 'height':
                         1024} HIP error: no kernel image is available for      
                         execution on the device                                
                         HIP kernel errors might be asynchronously reported at  
                         some other API call, so the stacktrace below might be  
                         incorrect.                                             
                         For debugging consider passing AMD_SERIALIZE_KERNEL=3  
                         Compile with `TORCH_USE_HIP_DSA` to enable device-side 
                         assertions.                                            

21:10:56-957327 ERROR    Processing: RuntimeError                               
╭───────────────────── Traceback (most recent call last) ──────────────────────╮
│ /home/noversi/Desktop/Image Generators/automatic/modules/processing_diffuser │
│                                                                              │
│    98 │   │   else:                                                          │
│ ❱  99 │   │   │   output = shared.sd_model(**base_args)                      │
│   100 │   │   if isinstance(output, dict):                                   │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│   115 │   │   with ctx_factory():                                            │
│ ❱ 116 │   │   │   return func(*args, **kwargs)                               │
│   117                                                                        │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│   1088 │   │   │   negative_pooled_prompt_embeds,                            │
│ ❱ 1089 │   │   ) = self.encode_prompt(                                       │
│   1090 │   │   │   prompt=prompt,                                            │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│    408 │   │   │   │                                                         │
│ ❱  409 │   │   │   │   prompt_embeds = text_encoder(text_input_ids.to(device │
│    410                                                                       │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│   1552 │   │   else:                                                         │
│ ❱ 1553 │   │   │   return self._call_impl(*args, **kwargs)                   │
│   1554                                                                       │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│   1561 │   │   │   │   or _global_forward_hooks or _global_forward_pre_hooks │
│ ❱ 1562 │   │   │   return forward_call(*args, **kwargs)                      │
│   1563                                                                       │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│    996 │   │                                                                 │
│ ❱  997 │   │   return self.text_model(                                       │
│    998 │   │   │   input_ids=input_ids,                                      │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│   1552 │   │   else:                                                         │
│ ❱ 1553 │   │   │   return self._call_impl(*args, **kwargs)                   │
│   1554                                                                       │
│                                                                              │
│                           ... 1 frames hidden ...                            │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│    887 │   │                                                                 │
│ ❱  888 │   │   hidden_states = self.embeddings(input_ids=input_ids, position │
│    889                                                                       │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│   1552 │   │   else:                                                         │
│ ❱ 1553 │   │   │   return self._call_impl(*args, **kwargs)                   │
│   1554                                                                       │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│   1561 │   │   │   │   or _global_forward_hooks or _global_forward_pre_hooks │
│ ❱ 1562 │   │   │   return forward_call(*args, **kwargs)                      │
│   1563                                                                       │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│    235 │   │   if inputs_embeds is None:                                     │
│ ❱  236 │   │   │   inputs_embeds = self.token_embedding(input_ids)           │
│    237                                                                       │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│   1552 │   │   else:                                                         │
│ ❱ 1553 │   │   │   return self._call_impl(*args, **kwargs)                   │
│   1554                                                                       │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│   1561 │   │   │   │   or _global_forward_hooks or _global_forward_pre_hooks │
│ ❱ 1562 │   │   │   return forward_call(*args, **kwargs)                      │
│   1563                                                                       │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│   163 │   def forward(self, input: Tensor) -> Tensor:                        │
│ ❱ 164 │   │   return F.embedding(                                            │
│   165 │   │   │   input, self.weight, self.padding_idx, self.max_norm,       │
│                                                                              │
│ /home/noversi/Desktop/Image Generators/automatic/venv/lib/python3.10/site-pa │
│                                                                              │
│   2266 │   │   _no_grad_embedding_renorm_(weight, input, max_norm, norm_type │
│ ❱ 2267 │   return torch.embedding(weight, input, padding_idx, scale_grad_by_ │
│   2268                                                                       │
╰──────────────────────────────────────────────────────────────────────────────╯
RuntimeError: HIP error: no kernel image is available for execution on the device
HIP kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing AMD_SERIALIZE_KERNEL=3
Compile with `TORCH_USE_HIP_DSA` to enable device-side assertions.

21:10:57-901720 DEBUG    Analyzed: model="talesOfDigitalLife_v131" type=sdxl    
                         class=StableDiffusionXLPipeline size=6938041464        
                         mtime="2024-10-02 08:20:54" modules=[name="vae"        
                         cls=AutoencoderKL config=True device=cuda:0            
                         dtype=torch.float32 params=83653863 modules=220,       
                         name="text_encoder" cls=CLIPTextModel config=True      
                         device=cuda:0 dtype=torch.float32 params=123060480     
                         modules=152, name="text_encoder_2"                     
                         cls=CLIPTextModelWithProjection config=True            
                         device=cuda:0 dtype=torch.float32 params=694659840     
                         modules=393, name="tokenizer" cls=CLIPTokenizer        
                         config=False, name="tokenizer_2" cls=CLIPTokenizer     
                         config=False, name="unet" cls=UNet2DConditionModel     
                         config=True device=cuda:0 dtype=torch.float32          
                         params=2567463684 modules=1911, name="scheduler"       
                         cls=EulerDiscreteScheduler config=True,                
                         name="image_encoder" cls=NoneType config=False,        
                         name="feature_extractor" cls=NoneType config=False,    
                         name="force_zeros_for_empty_prompt" cls=bool           
                         config=False]                                          
21:10:57-916630 INFO     Processed: images=0 its=0.00 time=1.01 timers={'init': 
                         0.02, 'process': 0.95} memory={'ram': {'used': 10.33,  
                         'total': 31.2}, 'gpu': {'used': 13.57, 'total': 23.98},
                         'retries': 0, 'oom': 0}

Backend

Diffusers

UI

Standard

Branch

Master

Model

StableDiffusion XL

Acknowledgements

Disty0 commented 3 days ago

You have a space in the Image Generators folder, spaces can cause weird issues.

Try renaming that folder to ImageGenerators without the space. But doing this will most likely require manually editing the venv config inside the venv folder or another clean install if you don't want to mess with configs.