[BUG] Problems getting latest beta to run

[vredesbyyrd]

Hi, thanks for sharing this awesome tool.

I'm struggling to get the latest beta to run. I installed iopaint in a virtual environment on arch linux. Models were originally installed in /.cache, but I set the --model-dir option in the below command hoping that re-downloading the models would help, but no dice. Any thoughts on what could be causing this? Thanks for your time.

System Info

• lama-cleaner: 1.2.2
• pytorch: 2.2.1

EDIT 2:

Downgrading 1 release version I no longer have any errors - pip install --force-reinstall -v "iopaint==1.2.0"

EDIT:

After rebooting my system I am still seeing errors, but there different. I can open the ui, but the model menu is empty.

iopaint start --model=lama --device=cpu --port=8080 --model-dir='/home/clu/build/python-iopaint/iopaint/models'
2024-03-15 18:17:36.514 | INFO     | iopaint.runtime:setup_model_dir:82 - Model directory: /home/clu/build/python-iopaint/iopaint/models
- Platform: Linux-6.7.9-arch1-1-x86_64-with-glibc2.39
- Python version: 3.11.8
- torch: 2.2.1
- torchvision: 0.17.1
- Pillow: 9.5.0
- diffusers: 0.26.3
- transformers: 4.38.2
- opencv-python: 4.9.0.80
- accelerate: 0.28.0
- iopaint: 1.2.2
- rembg: N/A
- realesrgan: N/A
- gfpgan: N/A

[W init.cpp:767] Warning: nvfuser is no longer supported in torch script, use _jit_set_nvfuser_enabled is deprecated and a no-op (function operator())
{
    "host": "127.0.0.1",
    "port": 8080,
    "inbrowser": false,
    "model": "lama",
    "no_half": false,
    "low_mem": false,
    "cpu_offload": false,
    "disable_nsfw_checker": false,
    "local_files_only": false,
    "cpu_textencoder": false,
    "device": "cpu",
    "input": null,
    "output_dir": null,
    "quality": 95,
    "enable_interactive_seg": false,
    "interactive_seg_model": "vit_b",
    "interactive_seg_device": "cpu",
    "enable_remove_bg": false,
    "remove_bg_model": "briaai/RMBG-1.4",
    "enable_anime_seg": false,
    "enable_realesrgan": false,
    "realesrgan_device": "cpu",
    "realesrgan_model": "realesr-general-x4v3",
    "enable_gfpgan": false,
    "gfpgan_device": "cpu",
    "enable_restoreformer": false,
    "restoreformer_device": "cpu"
}
2024-03-15 18:17:44.999 | INFO     | iopaint.model_manager:init_model:38 - Loading model: lama
2024-03-15 18:17:45.000 | INFO     | iopaint.helper:load_jit_model:107 - Loading model from: /home/clu/build/python-iopaint/iopaint/models/torch/hub/checkpoints/big-lama.pt
INFO:     Started server process [17912]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://127.0.0.1:8080 (Press CTRL+C to quit)
INFO:     127.0.0.1:36072 - "GET /socket.io/?EIO=4&transport=polling&t=Ov4Q6J0 HTTP/1.1" 200 OK
INFO:     127.0.0.1:36096 - "GET /api/v1/inputimage HTTP/1.1" 404 Not Found
INFO:     127.0.0.1:36080 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:36072 - "GET /api/v1/models HTTP/1.1" 404 Not Found
INFO:     127.0.0.1:36102 - "GET /api/v1/server-config HTTP/1.1" 200 OK
INFO:     127.0.0.1:36102 - "POST /socket.io/?EIO=4&transport=polling&t=Ov4Q6Kw&sid=WiQ9_QRPc1b-CQpHAAAA HTTP/1.1" 200 OK
INFO:     127.0.0.1:36080 - "GET /socket.io/?EIO=4&transport=polling&t=Ov4Q6Kx&sid=WiQ9_QRPc1b-CQpHAAAA HTTP/1.1" 200 OK
INFO:     ('127.0.0.1', 36112) - "WebSocket /socket.io/?EIO=4&transport=websocket&sid=WiQ9_QRPc1b-CQpHAAAA" [accepted]
INFO:     connection open
INFO:     127.0.0.1:36102 - "GET /socket.io/?EIO=4&transport=polling&t=Ov4Q6L5&sid=WiQ9_QRPc1b-CQpHAAAA HTTP/1.1" 200 OK
INFO:     127.0.0.1:36102 - "GET /socket.io/?EIO=4&transport=polling&t=Ov4Q6LH&sid=WiQ9_QRPc1b-CQpHAAAA HTTP/1.1" 200 OK
INFO:     127.0.0.1:36102 - "GET /socket.io/?EIO=4&transport=polling&t=Ov4Q6La&sid=WiQ9_QRPc1b-CQpHAAAA HTTP/1.1" 200 OK
INFO:     127.0.0.1:36102 - "GET /api/v1/models HTTP/1.1" 404 Not Found
INFO:     127.0.0.1:36102 - "GET /api/v1/models HTTP/1.1" 404 Not Found
INFO:     127.0.0.1:36102 - "GET /api/v1/models HTTP/1.1" 404 Not Found

[Sanster]

Model menu displays the models that have already been downloaded. When starting the service, specifying a model will automatically download it. For example, --model runwayml/stable-diffusion-inpainting. You can see more supported models here: https://www.iopaint.com/models.