[Feature]: Support for Flux depth and canny loras

[SAC020]

Issue Description

Using flux dev model with on-the-fly bnb quantization and balanced offload

Trying to use either flux depth or canny loras fails with

07:02:29-530344 WARNING Load network: type=LoRA name="flux1-canny-dev-lora" type=set() unmatched=1094 matched=0 07:02:29-536960 ERROR Load network: type=LoRA name="flux1-canny-dev-lora" detected=f1 failed

Version Platform Description

06:59:32-163410 INFO Python: version=3.11.9 platform=Windows bin="C:\ai\automatic\venv\Scripts\python.exe"
venv="C:\ai\automatic\venv"
06:59:32-398015 INFO Version: app=sd.next updated=2025-01-16 hash=e22d0789 branch=master
url=https://github.com/vladmandic/automatic/tree/master ui=main
06:59:33-066291 INFO Platform: arch=AMD64 cpu=Intel64 Family 6 Model 165 Stepping 5, GenuineIntel system=Windows
release=Windows-10-10.0.26100-SP0 python=3.11.9 docker=False

Relevant log output

PS C:\ai\automatic> .\webui.bat --debug
Using VENV: C:\ai\automatic\venv
06:59:32-158598 INFO     Starting SD.Next
06:59:32-161908 INFO     Logger: file="C:\ai\automatic\sdnext.log" level=DEBUG size=65 mode=create
06:59:32-163410 INFO     Python: version=3.11.9 platform=Windows bin="C:\ai\automatic\venv\Scripts\python.exe"
                         venv="C:\ai\automatic\venv"
06:59:32-398015 INFO     Version: app=sd.next updated=2025-01-16 hash=e22d0789 branch=master
                         url=https://github.com/vladmandic/automatic/tree/master ui=main
06:59:33-066291 INFO     Platform: arch=AMD64 cpu=Intel64 Family 6 Model 165 Stepping 5, GenuineIntel system=Windows
                         release=Windows-10-10.0.26100-SP0 python=3.11.9 docker=False
06:59:33-069313 DEBUG    Packages: venv=venv site=['venv', 'venv\\Lib\\site-packages']
06:59:33-070888 INFO     Args: ['--debug']
06:59:33-071885 DEBUG    Setting environment tuning
06:59:33-072884 DEBUG    Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512"
06:59:33-083746 DEBUG    Torch overrides: cuda=False rocm=False ipex=False directml=False openvino=False zluda=False
06:59:33-096881 INFO     CUDA: nVidia toolkit detected
06:59:33-274512 INFO     Install: verifying requirements
06:59:33-324837 DEBUG    Timestamp repository update time: Thu Jan 16 18:54:17 2025
06:59:33-326324 INFO     Startup: standard
06:59:33-327423 INFO     Verifying submodules
06:59:36-502867 DEBUG    Git submodule: extensions-builtin/sd-extension-chainner / main
06:59:36-598677 DEBUG    Git submodule: extensions-builtin/sd-extension-system-info / main
06:59:36-692804 DEBUG    Git submodule: extensions-builtin/sd-webui-agent-scheduler / main
06:59:36-833407 DEBUG    Git detached head detected: folder="extensions-builtin/sdnext-modernui" reattach=main
06:59:36-834895 DEBUG    Git submodule: extensions-builtin/sdnext-modernui / main
06:59:36-932952 DEBUG    Git submodule: extensions-builtin/stable-diffusion-webui-rembg / master
06:59:37-024661 DEBUG    Git submodule: modules/k-diffusion / master
06:59:37-122377 DEBUG    Git submodule: wiki / master
06:59:37-176912 DEBUG    Register paths
06:59:37-258164 DEBUG    Installed packages: 188
06:59:37-259444 DEBUG    Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sdnext-modernui', 'stable-diffusion-webui-rembg']
06:59:37-501037 DEBUG    Extension installer: C:\ai\automatic\extensions-builtin\sd-webui-agent-scheduler\install.py
06:59:39-770861 DEBUG    Extension installer: C:\ai\automatic\extensions-builtin\stable-diffusion-webui-rembg\install.py
06:59:46-144164 DEBUG    Extensions all: []
06:59:46-145155 INFO     Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sdnext-modernui', 'stable-diffusion-webui-rembg']
06:59:46-146147 INFO     Install: verifying requirements
06:59:46-147139 DEBUG    Setup complete without errors: 1737435586
06:59:46-152099 DEBUG    Extension preload: {'extensions-builtin': 0.0, 'extensions': 0.0}
06:59:46-153587 INFO     Command line args: ['--debug'] debug=True args=[]
06:59:46-154579 DEBUG    Env flags: []
06:59:46-155571 DEBUG    Starting module: <module 'webui' from 'C:\\ai\\automatic\\webui.py'>
06:59:54-028174 INFO     Device detect: memory=24.0 default=balanced
06:59:54-034266 DEBUG    Read: file="config.json" json=39 bytes=1793 time=0.000 fn=<module>:load
06:59:54-334309 INFO     Engine: backend=Backend.DIFFUSERS compute=cuda device=cuda attention="Scaled-Dot-Product"
                         mode=no_grad
06:59:54-335811 DEBUG    Read: file="html\reference.json" json=63 bytes=33413 time=0.000
                         fn=_call_with_frames_removed:<module>
06:59:54-389911 INFO     Torch parameters: backend=cuda device=cuda config=Auto dtype=torch.bfloat16 context=no_grad
                         nohalf=False nohalfvae=False upcast=False deterministic=False fp16=pass bf16=pass
                         optimization="Scaled-Dot-Product"
06:59:54-719671 DEBUG    ONNX: version=1.20.1 provider=CUDAExecutionProvider, available=['AzureExecutionProvider',
                         'CPUExecutionProvider']
06:59:54-901564 INFO     Device: device=NVIDIA GeForce RTX 4090 n=1 arch=sm_90 capability=(8, 9) cuda=12.4 cudnn=90100
                         driver=566.36
06:59:55-688443 INFO     Torch: torch==2.5.1+cu124 torchvision==0.20.1+cu124
06:59:55-689948 INFO     Packages: diffusers==0.33.0.dev0 transformers==4.47.1 accelerate==1.2.1 gradio==3.43.2
06:59:55-851881 DEBUG    Entering start sequence
06:59:55-856634 DEBUG    Initializing
06:59:55-865597 DEBUG    Read: file="metadata.json" json=172 bytes=411331 time=0.006 fn=initialize:init_metadata
06:59:55-867849 DEBUG    Huggingface cache: path="C:\Users\sebas\.cache\huggingface\hub"
06:59:55-952855 INFO     Available VAEs: path="models\VAE" items=0
06:59:55-955803 INFO     Available UNets: path="models\UNET" items=0
06:59:55-958325 INFO     Available TEs: path="models\Text-encoder" items=4
06:59:55-971068 INFO     Available Models: items=16 safetensors="models\Stable-diffusion":9
                         diffusers="models\Diffusers":7 time=0.01
06:59:56-003730 INFO     Available Styles: folder="models\styles" items=288 time=0.03
06:59:56-136184 INFO     Available Yolo: path="models\yolo" items=7 downloaded=3
06:59:56-139160 DEBUG    Extensions: disabled=['sdnext-modernui']
06:59:56-140648 INFO     Load extensions
06:59:56-254134 INFO     Available LoRAs: path="models\Lora" items=163 folders=3 time=0.01
06:59:56-501075 DEBUG    Register network: type=LoRA method=legacy
06:59:57-414029 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
06:59:57-418338 DEBUG    Extensions init time: total=1.28 sd-webui-agent-scheduler=0.86 Lora=0.27
06:59:57-428199 DEBUG    Read: file="html/upscalers.json" json=4 bytes=2672 time=0.001 fn=__init__:__init__
06:59:57-429847 DEBUG    Read: file="extensions-builtin\sd-extension-chainner\models.json" json=24 bytes=2719 time=0.000
                         fn=__init__:find_scalers
06:59:57-432713 DEBUG    chaiNNer models: path="models\chaiNNer" defined=24 discovered=0 downloaded=8
06:59:57-434726 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="1x-ITF-SkinDiffDetail-Lite-v1"
                         path="models\ESRGAN\1x-ITF-SkinDiffDetail-Lite-v1.pth"
06:59:57-435747 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4xNMKDSuperscale_4xNMKDSuperscale"
                         path="models\ESRGAN\4xNMKDSuperscale_4xNMKDSuperscale.pth"
06:59:57-436752 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4x_NMKD-Siax_200k"
                         path="models\ESRGAN\4x_NMKD-Siax_200k.pth"
06:59:57-440271 INFO     Available Upscalers: items=55 downloaded=11 user=3 time=0.02 types=['None', 'Lanczos',
                         'Nearest', 'ChaiNNer', 'AuraSR', 'ESRGAN', 'RealESRGAN', 'SCUNet', 'SD', 'SwinIR']
06:59:57-445234 DEBUG    UI start sequence
06:59:57-445974 WARNING  Networks: type=lora method=legacy
06:59:57-448030 INFO     UI theme: type=Standard name="black-teal" available=13
06:59:57-456852 DEBUG    UI theme: css="C:\ai\automatic\javascript\black-teal.css" base="sdnext.css" user="None"
06:59:57-459346 DEBUG    UI initialize: txt2img
06:59:57-735371 DEBUG    Networks: page='model' items=78 subfolders=2 tab=txt2img folders=['models\\Stable-diffusion',
                         'models\\Diffusers', 'models\\Reference'] list=0.07 thumb=0.01 desc=0.01 info=0.00 workers=8
06:59:57-740560 DEBUG    Networks: page='lora' items=163 subfolders=0 tab=txt2img folders=['models\\Lora',
                         'models\\LyCORIS'] list=0.08 thumb=0.02 desc=0.08 info=0.05 workers=8
06:59:57-749899 DEBUG    Networks: page='style' items=288 subfolders=1 tab=txt2img folders=['models\\styles', 'html']
                         list=0.07 thumb=0.00 desc=0.00 info=0.00 workers=8
06:59:57-753897 DEBUG    Networks: page='embedding' items=13 subfolders=0 tab=txt2img folders=['models\\embeddings']
                         list=0.05 thumb=0.02 desc=0.01 info=0.00 workers=8
06:59:57-755800 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
06:59:57-757691 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
06:59:58-052247 DEBUG    UI initialize: img2img
06:59:58-245923 DEBUG    UI initialize: control models=models\control
06:59:58-746674 DEBUG    Read: file="ui-config.json" json=0 bytes=2 time=0.000 fn=__init__:read_from_file
06:59:59-118995 DEBUG    Reading failed: C:\ai\automatic\html\extensions.json [Errno 2] No such file or directory:
                         'C:\\ai\\automatic\\html\\extensions.json'
06:59:59-119873 INFO     Extension list is empty: refresh required
06:59:59-647923 DEBUG    Extension list: processed=6 installed=6 enabled=5 disabled=1 visible=6 hidden=0
07:00:00-007507 DEBUG    Root paths: ['C:\\ai\\automatic']
07:00:00-104601 INFO     Local URL: http://127.0.0.1:7860/
07:00:00-107081 DEBUG    API middleware: [<class 'starlette.middleware.base.BaseHTTPMiddleware'>, <class
                         'starlette.middleware.gzip.GZipMiddleware'>]
07:00:00-110106 DEBUG    API initialize
07:00:00-312482 INFO     [AgentScheduler] Task queue is empty
07:00:00-313663 INFO     [AgentScheduler] Registering APIs
07:00:00-450242 DEBUG    Scripts setup: time=0.396 ['K-Diffusion Samplers:0.116', 'XYZ Grid:0.042', 'IP Adapters:0.036',
                         'Face: Multiple ID Transfers:0.017', 'Video: CogVideoX:0.011', 'FreeScale: Tuning-Free Scale
                         Fusion:0.01']
07:00:00-451240 DEBUG    Model metadata: file="metadata.json" no changes
07:00:00-453856 DEBUG    Model requested: fn=run:<lambda>
07:00:00-454992 INFO     Load model: select="Diffusers\black-forest-labs/FLUX.1-dev [0ef5fff789]"
07:00:00-459306 DEBUG    Load model: type=FLUX model="Diffusers\black-forest-labs/FLUX.1-dev"
                         repo="black-forest-labs/FLUX.1-dev" unet="None" te="None" vae="Automatic" quant=none
                         offload=balanced dtype=torch.bfloat16
07:00:00-984437 INFO     HF login: token="C:\Users\sebas\.cache\huggingface\token"
07:00:01-182852 DEBUG    GC: current={'gpu': 1.59, 'ram': 1.02, 'oom': 0} prev={'gpu': 1.6, 'ram': 1.02} load={'gpu': 7,
                         'ram': 2} gc={'gpu': 0.01, 'py': 11108} fn=load_diffuser_force:load_flux why=force time=0.20
07:00:01-185045 DEBUG    Load model: type=FLUX cls=FluxPipeline preloaded=[] revision=None
07:00:01-186472 DEBUG    Quantization: type=bitsandbytes version=0.45.0 fn=load_quants:create_bnb_config
07:00:01-188219 DEBUG    Quantization: module=all type=bnb dtype=nf4 storage=uint8
Diffusers 5971.96it/s ████████████████████ 100% 3/3 00:00 00:00 Fetching 3 files
07:00:23-722857 DEBUG    Quantization: module=transformer type=bnb dtype=nf4 storage=uint8
Downloading shards: 100%|██████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 1981.72it/s]
Diffusers  3.86s/it █████████████ 100% 2/2 00:07 00:00 Loading checkpoint shards
07:00:31-975264 DEBUG    Quantization: module=t5 type=bnb dtype=nf4 storage=uint8
07:00:31-977744 DEBUG    Quantization: module=all type=bnb dtype=nf4 storage=uint8
Diffusers  8.36it/s ████████ 100% 7/7 00:00 00:00 Loading pipeline components...
07:00:33-140642 DEBUG    Setting model: component=VAE slicing=True
07:00:33-152384 DEBUG    Setting model: attention="Scaled-Dot-Product"
07:00:33-184271 INFO     Offload: type=balanced op=init watermark=0.25-0.7 gpu=5.997-16.793:23.99 cpu=63.920 limit=0.00
07:00:35-695446 DEBUG    Model module=text_encoder_2 type=T5EncoderModel dtype=torch.bfloat16
                         quant=QuantizationMethod.BITS_AND_BYTES params=2.748 size=5.683
07:00:38-581734 DEBUG    Model module=transformer type=FluxTransformer2DModel dtype=torch.bfloat16
                         quant=QuantizationMethod.BITS_AND_BYTES params=5.543 size=5.546
07:00:38-583956 DEBUG    Model module=text_encoder type=CLIPTextModel dtype=torch.bfloat16 quant=None params=0.115
                         size=0.229
07:00:38-586229 DEBUG    Model module=vae type=AutoencoderKL dtype=torch.bfloat16 quant=None params=0.078 size=0.156
07:00:38-681399 INFO     Model class=FluxPipeline modules=4 size=11.615
07:00:38-689936 INFO     Load model: time=total=38.23 load=32.68 move=5.50 native=1024 memory={'ram': {'used': 19.23,
                         'total': 63.92}, 'gpu': {'used': 1.64, 'total': 23.99}, 'retries': 0, 'oom': 0}
07:00:38-693527 DEBUG    Script init: ['system-info.py:app_started=0.08', 'task_scheduler.py:app_started=0.15']
07:00:38-694664 INFO     Startup time: total=66.94 checkpoint=38.24 torch=23.94 launch=14.57 installer=14.41
                         extensions=1.28 ui-extensions=0.63 ui-networks=0.46 ui-settings=0.33 ui-defaults=0.26
                         ui-txt2img=0.26 app-started=0.23 ui-control=0.23 libraries=0.15 ui-img2img=0.14 detailer=0.13
                         api=0.11 samplers=0.10 ui-models=0.06 ui-extras=0.06 ui-gallery=0.06
07:00:38-696951 DEBUG    Save: file="config.json" json=39 bytes=1729 time=0.004
07:01:40-991697 INFO     API None 200 http/1.1 GET /sdapi/v1/motd 127.0.0.1 0.1742
07:01:44-562451 INFO     API None 200 http/1.1 GET /sdapi/v1/sd-models 127.0.0.1 0.003
07:01:44-966370 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/131.0.0.0 Safari/537.36 Edg/131.0.0.0
07:01:44-968989 INFO     API None 200 http/1.1 GET /sdapi/v1/start 127.0.0.1 0.0031
07:01:44-985326 INFO     UI: ready time=6.454
07:01:45-942677 DEBUG    UI: connected
07:01:59-740893 DEBUG    Server: alive=True requests=87 memory=19.24/63.92 status='running' task='Load'
                         timestamp='20250121070000' id='' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=129
                         elapsed=119.29 eta=None progress=0
07:02:26-539412 DEBUG    Pipeline class change: original=FluxPipeline target=FluxImg2ImgPipeline device=cpu
                         fn=process_images_inner:init
07:02:26-549007 DEBUG    Image resize: source=1024:1024 target=1024:1024 mode="Fixed" upscaler="None" type=image
                         time=0.00 fn=process_images_inner:init
07:02:26-566085 DEBUG    Sampler: "default" class=FlowMatchEulerDiscreteScheduler: {'num_train_timesteps': 1000,
                         'shift': 3.0, 'use_dynamic_shifting': True, 'base_shift': 0.5, 'max_shift': 1.15,
                         'base_image_seq_len': 256, 'max_image_seq_len': 4096, 'invert_sigmas': False, 'shift_terminal':
                         None, 'use_karras_sigmas': False, 'use_exponential_sigmas': False, 'use_beta_sigmas': False}
07:02:28-510537 DEBUG    Activate network: type=LoRA model="Diffusers\black-forest-labs/FLUX.1-dev [0ef5fff789]"
Load network: C:\ai\automatic\models\Lora\flux1-canny-dev-lora.safetensors ━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/1.2 GB -:--:--
07:02:28-641610 WARNING  Load network: type=LoRA name="flux1-canny-dev-lora" type=set() unmatched=1094 matched=0
07:02:28-648677 ERROR    Load network: type=LoRA name="flux1-canny-dev-lora" detected=f1 failed
07:02:29-239423 INFO     Base: pipeline=FluxImg2ImgPipeline task=IMAGE_2_IMAGE batch=1/1x1 set={'guidance_scale': 6,
                         'generator': 'cuda:[1778098256]', 'num_inference_steps': 67, 'output_type': 'latent', 'image':
                         [<PIL.Image.Image image mode=RGB size=1024x1024 at 0x23C56C1AA90>], 'strength': 0.3, 'width':
                         1024, 'height': 1024, 'parser': 'native', 'prompt': 'embeds'}
Load network: C:\ai\automatic\models\Lora\flux1-canny-dev-lora.safetensors ━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/1.2 GB -:--:--
07:02:29-530344 WARNING  Load network: type=LoRA name="flux1-canny-dev-lora" type=set() unmatched=1094 matched=0
07:02:29-536960 ERROR    Load network: type=LoRA name="flux1-canny-dev-lora" detected=f1 failed
Progress  1.08it/s ████▊                               14% 3/21 00:03 00:16 Base07:02:34-565380 DEBUG    VAE load: type=approximate model="models\VAE-approx\model.pt"
Progress  1.29it/s █████████████████████████████████ 100% 21/21 00:16 00:00 Base
07:02:49-503344 DEBUG    Decode: vae="default" upcast=False slicing=True tiling=False latents=torch.Size([1, 16, 128,
                         128]):cuda:0:torch.bfloat16 time=1.302
07:02:49-541757 DEBUG    Pipeline class change: original=FluxImg2ImgPipeline target=FluxPipeline device=cpu
                         fn=process_images:process_images_inner
07:02:49-543741 INFO     Processed: images=1 its=0.87 time=23.01 timers={'pipeline': 17.93, 'move': 2.98, 'decode':
                         2.04, 'encode': 1.94, 'offload': 1.31, 'gc': 0.11} memory={'ram': {'used': 20.2, 'total':
                         63.92}, 'gpu': {'used': 2.6, 'total': 23.99}, 'retries': 0, 'oom': 0}
07:02:49-777362 DEBUG    GC: current={'gpu': 2.09, 'ram': 20.2, 'oom': 0} prev={'gpu': 2.6, 'ram': 20.2} load={'gpu': 9,
                         'ram': 32} gc={'gpu': 0.51, 'py': 478} fn=process_images:process_images_inner why=final
                         time=0.23
07:02:50-103087 DEBUG    Save temp: image="C:\Users\sebas\AppData\Local\Temp\gradio\tmpczxo9b4y.png" width=1024
                         height=1024 size=1677227
07:03:00-950044 DEBUG    Pipeline class change: original=FluxPipeline target=FluxImg2ImgPipeline device=cpu
                         fn=process_images_inner:init
07:03:00-962612 DEBUG    Image resize: source=1024:1024 target=1024:1024 mode="Fixed" upscaler="None" type=image
                         time=0.00 fn=process_images_inner:init
07:03:00-965051 DEBUG    Sampler: "default" class=FlowMatchEulerDiscreteScheduler: {'num_train_timesteps': 1000,
                         'shift': 3.0, 'use_dynamic_shifting': True, 'base_shift': 0.5, 'max_shift': 1.15,
                         'base_image_seq_len': 256, 'max_image_seq_len': 4096, 'invert_sigmas': False, 'shift_terminal':
                         None, 'use_karras_sigmas': False, 'use_exponential_sigmas': False, 'use_beta_sigmas': False}
Load network: C:\ai\automatic\models\Lora\flux1-depth-dev-lora.safetensors ━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/1.2 GB -:--:--
07:03:01-982519 WARNING  Load network: type=LoRA name="flux1-depth-dev-lora" type=set() unmatched=1094 matched=0
07:03:01-989746 ERROR    Load network: type=LoRA name="flux1-depth-dev-lora" detected=f1 failed
07:03:02-556206 INFO     Base: pipeline=FluxImg2ImgPipeline task=IMAGE_2_IMAGE batch=1/1x1 set={'guidance_scale': 6,
                         'generator': 'cuda:[2178962404]', 'num_inference_steps': 67, 'output_type': 'latent', 'image':
                         [<PIL.Image.Image image mode=RGB size=1024x1024 at 0x23C56F78310>], 'strength': 0.3, 'width':
                         1024, 'height': 1024, 'parser': 'native', 'prompt': 'embeds'}
Load network: C:\ai\automatic\models\Lora\flux1-depth-dev-lora.safetensors ━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/1.2 GB -:--:--
07:03:02-619535 WARNING  Load network: type=LoRA name="flux1-depth-dev-lora" type=set() unmatched=1094 matched=0
07:03:02-626374 ERROR    Load network: type=LoRA name="flux1-depth-dev-lora" detected=f1 failed
Progress  1.29it/s █████████████████████████████████ 100% 21/21 00:16 00:00 Base
07:03:19-942222 DEBUG    Decode: vae="default" upcast=False slicing=True tiling=False latents=torch.Size([1, 16, 128,
                         128]):cuda:0:torch.bfloat16 time=0.027
07:03:20-111577 DEBUG    Pipeline class change: original=FluxImg2ImgPipeline target=FluxPipeline device=cpu
                         fn=process_images:process_images_inner
07:03:20-113595 INFO     Processed: images=1 its=1.04 time=19.16 timers={'pipeline': 16.55, 'move': 1.67, 'offload':
                         1.32, 'decode': 0.9, 'encode': 0.85, 'gc': 0.11} memory={'ram': {'used': 20.16, 'total':
                         63.92}, 'gpu': {'used': 7.01, 'total': 23.99}, 'retries': 0, 'oom': 0}
07:03:20-365659 DEBUG    GC: current={'gpu': 2.09, 'ram': 20.16, 'oom': 0} prev={'gpu': 7.01, 'ram': 20.16} load={'gpu':
                         9, 'ram': 32} gc={'gpu': 4.92, 'py': 303} fn=process_images:process_images_inner why=final
                         time=0.25
07:03:20-690552 DEBUG    Save temp: image="C:\Users\sebas\AppData\Local\Temp\gradio\tmpnxuwm0zl.png" width=1024
                         height=1024 size=1687176

Backend

Diffusers

UI

Standard

Branch

Master

Model

FLUX.1

Acknowledgements

• I have read the above and searched for existing issues
• I confirm that this is classified correctly and its not an extension issue

[vladmandic]

From changelog, its actually explicitly written that Depth/Canny LoRAs are NOT supported at the moment.

They are not normal LoRAs by any means. I could add support, but then it would require same silly handholding for preparing input params as using Depth/Canny standalone models which is counter-intuitive for LoRA usage.
If there is large demand, I'll add it.
For now, converting this issue into feature request.