[Issue]: black images on Intel Arc A770 (without errors)
AndrewRainfall opened this issue · comments
Issue Description
Generation in img2img & text2img results in black images without errors. Yesterday it worked fine with the same settings.
My default settings (Autocast, BF16) give only black images.
I tried to different combinations of compute settings, sometimes I get one image with (Full, FP16, --no-half, --no-half-vae).
What happened & how to fix this?
Version Platform Description
Using VENV: C:\automatic\venv
18:38:40-538465 INFO Starting SD.Next
18:38:40-544467 INFO Logger: file="C:\automatic\sdnext.log" level=DEBUG size=65 mode=create
18:38:40-547468 INFO Python 3.10.11 on Windows
18:38:40-833202 INFO Version: app=sd.next updated=2024-04-21 hash=de267390 branch=master
url=https://github.com/vladmandic/automatic/tree/master
18:38:41-465631 INFO Platform: arch=AMD64 cpu=AMD64 Family 23 Model 8 Stepping 2, AuthenticAMD system=Windows
release=Windows-10-10.0.19045-SP0 python=3.10.11
18:38:41-469630 DEBUG Setting environment tuning
18:38:41-471631 DEBUG HF cache folder: C:\Users\Rain.cache\huggingface\hub
18:38:41-473631 DEBUG Torch overrides: cuda=False rocm=False ipex=True diml=False openvino=False
18:38:41-475632 DEBUG Torch allowed: cuda=False rocm=False ipex=True diml=False openvino=False
18:38:41-478632 INFO Intel OneAPI Toolkit detected
18:38:41-481633 DEBUG Installing torch:
https://github.com/Nuullll/intel-extension-for-pytorch/releases/download/v2.1.10%2Bxpu/torch-2
.1.0a0+cxx11.abi-cp310-cp310-win_amd64.whl
https://github.com/Nuullll/intel-extension-for-pytorch/releases/download/v2.1.10%2Bxpu/torchvi
sion-0.16.0a0+cxx11.abi-cp310-cp310-win_amd64.whl
https://github.com/Nuullll/intel-extension-for-pytorch/releases/download/v2.1.10%2Bxpu/intel_e
xtension_for_pytorch-2.1.10+xpu-cp310-cp310-win_amd64.whl
18:38:41-583657 INFO Startup: standard
18:38:41-585657 INFO Verifying requirements
18:38:41-602660 INFO Verifying packages
18:38:41-604661 INFO Verifying submodules
18:38:45-507309 DEBUG Submodule: extensions-builtin/sd-extension-chainner / main
18:38:46-721425 DEBUG Submodule: extensions-builtin/sd-extension-system-info / main
18:38:47-828678 DEBUG Submodule: extensions-builtin/sd-webui-agent-scheduler / main
18:38:48-990164 DEBUG Submodule: extensions-builtin/sd-webui-controlnet / main
18:38:50-437015 DEBUG Submodule: extensions-builtin/stable-diffusion-webui-images-browser / main
18:38:51-568201 DEBUG Submodule: extensions-builtin/stable-diffusion-webui-rembg / master
18:38:52-689188 DEBUG Submodule: modules/k-diffusion / master
18:38:53-810676 DEBUG Submodule: wiki / master
18:38:54-908287 DEBUG Register paths
18:38:55-220357 DEBUG Installed packages: 260
18:38:55-223357 DEBUG Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info', 'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
18:38:56-522841 DEBUG Submodule: extensions-builtin\sd-extension-chainner / main
18:38:57-918223 DEBUG Submodule: extensions-builtin\sd-extension-system-info / main
18:38:58-936983 DEBUG Running extension installer: C:\automatic\extensions-builtin\sd-extension-system-info\install.py
18:38:59-931208 DEBUG Submodule: extensions-builtin\sd-webui-agent-scheduler / main
18:39:00-922296 DEBUG Running extension installer: C:\automatic\extensions-builtin\sd-webui-agent-scheduler\install.py
18:39:01-914419 DEBUG Submodule: extensions-builtin\sd-webui-controlnet / main
18:39:03-426755 DEBUG Running extension installer: C:\automatic\extensions-builtin\sd-webui-controlnet\install.py
18:39:04-585866 DEBUG Submodule: extensions-builtin\stable-diffusion-webui-images-browser / main
18:39:05-597187 DEBUG Running extension installer: C:\automatic\extensions-builtin\stable-diffusion-webui-images-browser\install.py
18:39:06-586184 DEBUG Submodule: extensions-builtin\stable-diffusion-webui-rembg / master
18:39:07-585117 DEBUG Running extension installer: C:\automatic\extensions-builtin\stable-diffusion-webui-rembg\install.py
18:39:08-471336 DEBUG Extensions all: ['sd-webui-reactor']
18:39:08-595011 DEBUG Submodule: extensions\sd-webui-reactor / main
18:39:09-586783 DEBUG Running extension installer: C:\automatic\extensions\sd-webui-reactor\install.py
18:39:12-992752 INFO Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info', 'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg',
'sd-webui-reactor']
Relevant log output
Using VENV: C:\automatic\venv
18:38:40-538465 INFO Starting SD.Next
18:38:40-544467 INFO Logger: file="C:\automatic\sdnext.log" level=DEBUG size=65 mode=create
18:38:40-547468 INFO Python 3.10.11 on Windows
18:38:40-833202 INFO Version: app=sd.next updated=2024-04-21 hash=de267390 branch=master
url=https://github.com/vladmandic/automatic/tree/master
18:38:41-465631 INFO Platform: arch=AMD64 cpu=AMD64 Family 23 Model 8 Stepping 2, AuthenticAMD system=Windows
release=Windows-10-10.0.19045-SP0 python=3.10.11
18:38:41-469630 DEBUG Setting environment tuning
18:38:41-471631 DEBUG HF cache folder: C:\Users\Rain\.cache\huggingface\hub
18:38:41-473631 DEBUG Torch overrides: cuda=False rocm=False ipex=True diml=False openvino=False
18:38:41-475632 DEBUG Torch allowed: cuda=False rocm=False ipex=True diml=False openvino=False
18:38:41-478632 INFO Intel OneAPI Toolkit detected
18:38:41-481633 DEBUG Installing torch:
https://github.com/Nuullll/intel-extension-for-pytorch/releases/download/v2.1.10%2Bxpu/torch-2
.1.0a0+cxx11.abi-cp310-cp310-win_amd64.whl
https://github.com/Nuullll/intel-extension-for-pytorch/releases/download/v2.1.10%2Bxpu/torchvi
sion-0.16.0a0+cxx11.abi-cp310-cp310-win_amd64.whl
https://github.com/Nuullll/intel-extension-for-pytorch/releases/download/v2.1.10%2Bxpu/intel_e
xtension_for_pytorch-2.1.10+xpu-cp310-cp310-win_amd64.whl
18:38:41-583657 INFO Startup: standard
18:38:41-585657 INFO Verifying requirements
18:38:41-602660 INFO Verifying packages
18:38:41-604661 INFO Verifying submodules
18:38:45-507309 DEBUG Submodule: extensions-builtin/sd-extension-chainner / main
18:38:46-721425 DEBUG Submodule: extensions-builtin/sd-extension-system-info / main
18:38:47-828678 DEBUG Submodule: extensions-builtin/sd-webui-agent-scheduler / main
18:38:48-990164 DEBUG Submodule: extensions-builtin/sd-webui-controlnet / main
18:38:50-437015 DEBUG Submodule: extensions-builtin/stable-diffusion-webui-images-browser / main
18:38:51-568201 DEBUG Submodule: extensions-builtin/stable-diffusion-webui-rembg / master
18:38:52-689188 DEBUG Submodule: modules/k-diffusion / master
18:38:53-810676 DEBUG Submodule: wiki / master
18:38:54-908287 DEBUG Register paths
18:38:55-220357 DEBUG Installed packages: 260
18:38:55-223357 DEBUG Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info', 'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
18:38:56-522841 DEBUG Submodule: extensions-builtin\sd-extension-chainner / main
18:38:57-918223 DEBUG Submodule: extensions-builtin\sd-extension-system-info / main
18:38:58-936983 DEBUG Running extension installer: C:\automatic\extensions-builtin\sd-extension-system-info\install.py
18:38:59-931208 DEBUG Submodule: extensions-builtin\sd-webui-agent-scheduler / main
18:39:00-922296 DEBUG Running extension installer: C:\automatic\extensions-builtin\sd-webui-agent-scheduler\install.py
18:39:01-914419 DEBUG Submodule: extensions-builtin\sd-webui-controlnet / main
18:39:03-426755 DEBUG Running extension installer: C:\automatic\extensions-builtin\sd-webui-controlnet\install.py
18:39:04-585866 DEBUG Submodule: extensions-builtin\stable-diffusion-webui-images-browser / main
18:39:05-597187 DEBUG Running extension installer: C:\automatic\extensions-builtin\stable-diffusion-webui-images-browser\install.py
18:39:06-586184 DEBUG Submodule: extensions-builtin\stable-diffusion-webui-rembg / master
18:39:07-585117 DEBUG Running extension installer: C:\automatic\extensions-builtin\stable-diffusion-webui-rembg\install.py
18:39:08-471336 DEBUG Extensions all: ['sd-webui-reactor']
18:39:08-595011 DEBUG Submodule: extensions\sd-webui-reactor / main
18:39:09-586783 DEBUG Running extension installer: C:\automatic\extensions\sd-webui-reactor\install.py
18:39:12-992752 INFO Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info', 'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg',
'sd-webui-reactor']
18:39:12-995753 INFO Verifying requirements
18:39:13-012757 INFO Updating Wiki
18:39:13-135785 DEBUG Submodule: C:\automatic\wiki / master
18:39:14-144047 DEBUG Setup complete without errors: 1714405154
18:39:14-152049 DEBUG Extension preload: {'extensions-builtin': 0.0, 'extensions': 0.0}
18:39:14-155050 DEBUG Starting module: <module 'webui' from 'C:\\automatic\\webui.py'>
18:39:14-158050 INFO Command line args: ['--use-ipex', '--upgrade', '--debug', '--autolaunch'] autolaunch=True upgrade=True use_ipex=True debug=True
18:39:14-161051 DEBUG Env flags: []
18:39:18-570169 DEBUG Load IPEX==2.1.10+xpu
18:39:22-915406 INFO Load packages: {'torch': '2.1.0a0+cxx11.abi', 'diffusers': '0.27.0', 'gradio': '3.43.2'}
18:39:24-206698 DEBUG Read: file="config.json" json=51 bytes=2536 time=0.000
18:39:24-210700 INFO Engine: backend=Backend.DIFFUSERS compute=ipex device=xpu attention="Scaled-Dot-Product" mode=no_grad
18:39:24-214700 INFO Device: device=Intel(R) Arc(TM) A770 Graphics n=1 ipex=2.1.10+xpu
18:39:24-217701 DEBUG Read: file="html\reference.json" json=36 bytes=21493 time=0.000
18:39:24-937873 DEBUG ONNX: version=1.17.1 provider=OpenVINOExecutionProvider, available=['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider']
18:39:25-052890 DEBUG Importing LDM
18:39:25-077896 DEBUG Entering start sequence
18:39:25-081898 DEBUG Initializing
18:39:25-112174 INFO Available VAEs: path="E:\models\VAE" items=4
18:39:25-116175 INFO Disabled extensions: ['sd-webui-controlnet']
18:39:25-120177 DEBUG Scanning diffusers cache: folder=models\Diffusers items=0 time=0.00
18:39:25-124177 DEBUG Read: file="cache.json" json=1 bytes=3735 time=0.000
18:39:25-128179 DEBUG Read: file="metadata.json" json=90 bytes=108980 time=0.001
18:39:25-134180 INFO Available models: path="E:\models\Stable-diffusion" items=20 time=0.02
18:39:25-216198 DEBUG Load extensions
18:39:25-276211 INFO Extension: script='extensions-builtin\Lora\scripts\lora_script.py' 18:39:25-271210 INFO LoRA networks: available=14 folders=2
18:39:25-890351 INFO Extension: script='extensions-builtin\sd-webui-agent-scheduler\scripts\task_scheduler.py' Using sqlite file: extensions-builtin\sd-webui-agent-scheduler\task_scheduler.sqlite3
18:39:26-415895 DEBUG Extensions init time: 1.20 sd-webui-agent-scheduler=0.57 stable-diffusion-webui-images-browser=0.30 sd-webui-reactor=0.21
18:39:26-436130 DEBUG Read: file="html/upscalers.json" json=4 bytes=2672 time=0.000
18:39:26-439118 DEBUG Read: file="extensions-builtin\sd-extension-chainner\models.json" json=24 bytes=2719 time=0.000
18:39:26-444129 DEBUG chaiNNer models: path="models\chaiNNer" defined=24 discovered=0 downloaded=0
18:39:26-450130 DEBUG Upscaler type=ESRGAN folder="models\ESRGAN" model="4x-UltraSharp" path="models\ESRGAN\4x-UltraSharp.pth"
18:39:26-453122 DEBUG Upscaler type=ESRGAN folder="models\ESRGAN" model="4x_NickelbackFS_72000_G" path="models\ESRGAN\4x_NickelbackFS_72000_G.pth"
18:39:26-456143 DEBUG Upscaler type=ESRGAN folder="models\ESRGAN" model="4x_NMKD-Siax_200k" path="models\ESRGAN\4x_NMKD-Siax_200k.pth"
18:39:26-463145 DEBUG Load upscalers: total=55 downloaded=6 user=3 time=0.04 ['None', 'Lanczos', 'Nearest', 'ChaiNNer', 'ESRGAN', 'LDSR', 'RealESRGAN', 'SCUNet', 'SD', 'SwinIR']
18:39:26-498145 DEBUG Load styles: folder="models\styles" items=288 time=0.03
18:39:26-504147 DEBUG Creating UI
18:39:26-507148 INFO UI theme: name="black-teal" style=Dark base=sdnext.css
18:39:26-523150 DEBUG UI initialize: txt2img
18:39:26-622173 DEBUG Extra networks: page='style' items=288 subfolders=1 tab=txt2img folders=['models\\styles', 'html'] list=0.03 thumb=0.00 desc=0.00 info=0.00 workers=4
18:39:26-630175 DEBUG Extra networks: page='embedding' items=7 subfolders=0 tab=txt2img folders=['models\\embeddings'] list=0.01 thumb=0.00 desc=0.00 info=0.00 workers=4
18:39:26-641178 DEBUG Extra networks: page='lora' items=14 subfolders=6 tab=txt2img folders=['E:\\models\\Lora', 'models\\LyCORIS'] list=0.02 thumb=0.01 desc=0.01 info=0.01 workers=4
18:39:26-766206 DEBUG UI initialize: img2img
18:39:26-931243 DEBUG UI initialize: control models=models\control
18:39:27-301327 DEBUG Read: file="ui-config.json" json=61 bytes=4597 time=0.000
18:39:27-422354 DEBUG Themes: builtin=12 gradio=5 huggingface=0
18:39:28-411587 INFO Extension list is empty: refresh required
18:39:29-478025 DEBUG Extension list: processed=8 installed=8 enabled=7 disabled=1 visible=8 hidden=0
18:39:29-722081 DEBUG Root paths: ['C:\\automatic']
18:39:29-844904 INFO Local URL: http://127.0.0.1:7860/
18:39:29-846905 DEBUG Gradio functions: registered=2190
18:39:29-849906 DEBUG FastAPI middleware: ['Middleware', 'Middleware']
18:39:29-854907 DEBUG Creating API
18:39:30-329024 INFO [AgentScheduler] Task queue is empty
18:39:30-331014 INFO [AgentScheduler] Registering APIs
18:39:30-530068 DEBUG Scripts setup: ['IP Adapters:0.023', 'AnimateDiff:0.014', 'ReActor:0.054', 'Prompt Matrix:0.005', 'Prompts from File:0.005', 'X/Y/Z Grid:0.02', 'Face:0.019', 'Image-to-Video:0.01', 'LEdits++:0.006', 'Stable
Video Diffusion:0.008']
18:39:30-534060 DEBUG Model metadata: file="metadata.json" no changes
18:39:30-537062 DEBUG Model requested: fn=<lambda>
18:39:30-539062 INFO Select: refiner="Photos\cyberrealistic_v42 [ea1b665634]"
18:39:30-543062 DEBUG Load model: existing=False target=E:\models\Stable-diffusion\Photos\cyberrealistic_v42.safetensors info=None
18:39:30-867518 DEBUG Desired Torch parameters: dtype=BF16 no-half=False no-half-vae=False upscast=False
18:39:30-871520 INFO Setting Torch parameters: device=xpu dtype=torch.bfloat16 vae=torch.bfloat16 unet=torch.bfloat16 context=no_grad fp16=True bf16=True optimization=Scaled-Dot-Product
18:39:30-874521 INFO Loading VAE: model=E:\models\VAE\vae-ft-mse-840000-ema-pruned.safetensors source=settings
18:39:30-877521 DEBUG Diffusers VAE load config: {'low_cpu_mem_usage': False, 'torch_dtype': torch.bfloat16, 'use_safetensors': True, 'force_upcast': False}
18:39:30-879522 INFO Autodetect: vae="Stable Diffusion" class=StableDiffusionPipeline file="E:\models\Stable-diffusion\Photos\cyberrealistic_v42.safetensors" size=2034MB
18:39:31-128577 DEBUG Diffusers loading: path="E:\models\Stable-diffusion\Photos\cyberrealistic_v42.safetensors"
18:39:31-131578 INFO Autodetect: refiner="Stable Diffusion" class=StableDiffusionPipeline file="E:\models\Stable-diffusion\Photos\cyberrealistic_v42.safetensors" size=2034MB
18:39:34-756322 DEBUG Setting refiner: pipeline=StableDiffusionPipeline config={'low_cpu_mem_usage': True, 'torch_dtype': torch.bfloat16, 'load_connected_pipeline': True, 'extract_ema': True, 'original_config_file':
'configs/v1-inference.yaml', 'use_safetensors': True}
18:39:34-762323 DEBUG Setting refiner VAE: name=vae-ft-mse-840000-ema-pruned.safetensors
18:39:34-765324 DEBUG Setting refiner VAE: upcast=True
18:39:34-767324 DEBUG Setting refiner: enable VAE slicing
18:39:34-769325 DEBUG Setting refiner: enable VAE tiling
18:39:34-779327 DEBUG Moving refiner model to CPU
18:39:34-799332 DEBUG Model requested: fn=load_textual_inversion_embeddings
18:39:35-027384 DEBUG GC: collected=8145 device=xpu {'ram': {'used': 2.87, 'total': 31.95}, 'gpu': {'used': 0.0, 'total': 15.54}, 'retries': 0, 'oom': 0} time=0.23
18:39:35-033385 DEBUG Model requested: fn=assign_network_names_to_compvis_modules
18:39:35-035386 INFO Load refiner: time=4.26 load=4.26 native=512 {'ram': {'used': 2.87, 'total': 31.95}, 'gpu': {'used': 0.0, 'total': 15.54}, 'retries': 0, 'oom': 0}
18:39:35-041388 DEBUG Script callback init time: image_browser.py:ui_tabs=0.63 system-info.py:app_started=0.10 task_scheduler.py:app_started=0.22
18:39:35-043387 DEBUG Save: file="config.json" json=51 bytes=2461 time=0.002
18:39:35-049853 INFO Startup time: 20.88 torch=7.35 olive=0.10 gradio=1.30 libraries=2.14 extensions=1.20 face-restore=0.08 upscalers=0.05 ui-en=0.27 ui-txt2img=0.09 ui-img2img=0.12 ui-control=0.17 ui-extras=0.07 ui-models=0.05
ui-settings=0.47 ui-extensions=1.74 ui-defaults=0.14 launch=0.22 api=0.36 app-started=0.32 checkpoint=4.51
18:39:35-064857 INFO Launching browser
18:39:38-461670 INFO MOTD: N/A
18:39:44-814108 DEBUG Themes: builtin=12 gradio=5 huggingface=0
18:39:47-712765 INFO Browser session: user=None client=127.0.0.1 agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36
18:40:00-494914 DEBUG Server: alive=True jobs=1 requests=21 uptime=37 memory=2.88/31.95 backend=Backend.DIFFUSERS state=idle
18:40:11-790937 DEBUG Model requested: fn=update_token_counter
18:40:11-793938 INFO Select: model="Photos\cyberrealistic_v42 [ea1b665634]"
18:40:11-796940 DEBUG Load model: existing=False target=E:\models\Stable-diffusion\Photos\cyberrealistic_v42.safetensors info=None
18:40:11-804940 DEBUG Desired Torch parameters: dtype=BF16 no-half=False no-half-vae=False upscast=False
18:40:11-807941 INFO Setting Torch parameters: device=xpu dtype=torch.bfloat16 vae=torch.bfloat16 unet=torch.bfloat16 context=no_grad fp16=True bf16=True optimization=Scaled-Dot-Product
18:40:11-812942 INFO Loading VAE: model=E:\models\VAE\vae-ft-mse-840000-ema-pruned.safetensors source=settings
18:40:11-815943 DEBUG Diffusers VAE load config: {'low_cpu_mem_usage': False, 'torch_dtype': torch.bfloat16, 'use_safetensors': True, 'force_upcast': False}
18:40:11-818943 INFO Autodetect: vae="Stable Diffusion" class=StableDiffusionPipeline file="E:\models\Stable-diffusion\Photos\cyberrealistic_v42.safetensors" size=2034MB
18:40:12-134014 DEBUG Diffusers loading: path="E:\models\Stable-diffusion\Photos\cyberrealistic_v42.safetensors"
18:40:12-137016 INFO Autodetect: model="Stable Diffusion" class=StableDiffusionPipeline file="E:\models\Stable-diffusion\Photos\cyberrealistic_v42.safetensors" size=2034MB
18:40:15-617877 DEBUG Setting model: pipeline=StableDiffusionPipeline config={'low_cpu_mem_usage': True, 'torch_dtype': torch.bfloat16, 'load_connected_pipeline': True, 'extract_ema': True, 'original_config_file':
'configs/v1-inference.yaml', 'use_safetensors': True}
18:40:15-623879 DEBUG Setting model VAE: name=vae-ft-mse-840000-ema-pruned.safetensors
18:40:15-625879 DEBUG Setting model VAE: upcast=True
18:40:15-627879 DEBUG Setting model: enable VAE slicing
18:40:15-630880 DEBUG Setting model: enable VAE tiling
18:40:18-858104 INFO Load embeddings: loaded=6 skipped=1 time=0.88
18:40:19-098158 DEBUG GC: collected=249 device=xpu {'ram': {'used': 3.12, 'total': 31.95}, 'gpu': {'used': 2.13, 'total': 15.54}, 'retries': 0, 'oom': 0} time=0.24
18:40:19-109160 INFO Load model: time=7.06 load=7.06 native=512 {'ram': {'used': 3.12, 'total': 31.95}, 'gpu': {'used': 2.13, 'total': 15.54}, 'retries': 0, 'oom': 0}
18:40:35-312569 DEBUG Pipeline class change: original=StableDiffusionPipeline target=StableDiffusionImg2ImgPipeline device=xpu:0 fn=init
18:40:35-501612 INFO Base: class=StableDiffusionImg2ImgPipeline
18:40:41-699792 DEBUG Diffuser pipeline: StableDiffusionImg2ImgPipeline task=DiffusersTaskType.IMAGE_2_IMAGE set={'prompt_embeds': torch.Size([2, 1463, 768]), 'negative_prompt_embeds': torch.Size([2, 1463, 768]), 'guidance_scale': 3,
'generator': device(type='xpu'), 'num_inference_steps': 93, 'eta': 1.0, 'output_type': 'latent', 'image': [<PIL.Image.Image image mode=RGB size=1200x1200 at 0x2022413BA00>, <PIL.Image.Image image mode=RGB
size=1200x1200 at 0x2027F09E0E0>], 'strength': 0.38, 'parser': 'Full parser'}
18:40:43-484818 DEBUG Sampler: sampler="DPM++ 2M" config={'num_train_timesteps': 1000, 'beta_start': 0.00085, 'beta_end': 0.012, 'beta_schedule': 'scaled_linear', 'prediction_type': 'epsilon', 'thresholding': False,
'sample_max_value': 1.0, 'algorithm_type': 'sde-dpmsolver++', 'solver_type': 'midpoint', 'lower_order_final': True, 'use_karras_sigmas': True, 'final_sigmas_type': 'zero'}
Progress 8.69s/it █▉ 6% 2/35 00:18 04:46 Base18:41:32-857539 DEBUG VAE load: type=approximate model=models\VAE-approx\model.pt
Progress 3.73s/it ████████▋ 26% 9/35 00:45 01:37 Base18:41:59-575621 DEBUG Server: alive=True jobs=1 requests=148 uptime=156 memory=4.08/31.95 backend=Backend.DIFFUSERS state=idle
Progress 3.86s/it █████████████████████████████████ 100% 35/35 02:15 00:00 Base
18:43:27-685149 DEBUG Moving to CPU: model=UNet
18:43:51-737354 DEBUG Applying color correction: correction=(1200, 1200, 3) image=<PIL.Image.Image image mode=RGB size=1200x1200 at 0x202259AB250>
18:44:06-369665 INFO Saving: image="F:\06_STABLE_DIFFUSION\outputs\00560-cyberrealistic_v42-candid photo of a man in a shirt.jpg" type=JPEG resolution=1200x1200 size=0
18:44:06-374667 WARNING Saving: removing alpha channel
18:44:06-988873 DEBUG Applying color correction: correction=(1200, 1200, 3) image=<PIL.Image.Image image mode=RGB size=1200x1200 at 0x2022F55E470>
18:44:21-450010 INFO Saving: image="F:\06_STABLE_DIFFUSION\outputs\00561-cyberrealistic_v42-candid photo of a man in a shirt.jpg" type=JPEG resolution=1200x1200 size=0
18:44:21-454012 WARNING Saving: removing alpha channel
18:44:21-780462 INFO Processed: images=2 time=226.47 its=0.31 memory={'ram': {'used': 4.37, 'total': 31.95}, 'gpu': {'used': 8.24, 'total': 15.54}, 'retries': 0, 'oom': 0}
18:44:21-800467 INFO Saving: image="F:\06_STABLE_DIFFUSION\outputs\99_Grids\00081-cyberrealistic_v42-candid photo of a man in a shirt-grid.jpg" type=JPEG resolution=2400x1200 size=0Backend
Diffusers
Branch
Master
Model
SD 1.5
Acknowledgements
- I have read the above and searched for existing issues
- I confirm that this is classified correctly and its not an extension issue
Somehow it's fixed now.