Dont work at all for me

[Archer7x]

GTX 1080 Ti 12Gb VRam
Windows 11 CMD:
`S:\AI-Tools\Aitrepreneur>cd OmniGen

S:\AI-Tools\Aitrepreneur\OmniGen>LAUNCHER.bat
S:\AI-Tools\Aitrepreneur\OmniGen\app.py:229: SyntaxWarning: invalid escape sequence '/'
"<|image_1|></img> What item can be used to see the current time? Please highlight it in blue.",
S:\AI-Tools\Aitrepreneur\OmniGen\app.py:271: SyntaxWarning: invalid escape sequence '<'
description = """
Fetching 10 files: 100%|███████████████████████████████████████████████████████████████████████| 10/10 [00:00<?, ?it/s]
Loading safetensors

(env) S:\AI-Tools\Aitrepreneur\OmniGen>`
Please help me :C

[Archer7x]

I used this script:
OMNIGEN_AUTO_INSTALL.bat
And tried it manually

[nitinmukesh]

See if this works
https://youtu.be/9ZXmXA2AJZ4?si=M2kESfsCh-LO-5Ky

[Archer7x]

Thank you very much! The fork from the video at least starts, but when I start the generation it stops:

(omnigen) S:\AI-Tools\omnigen>python app.py
INFORMATION: Es konnten keine Dateien mit dem angegebenen
Muster gefunden werden.

• Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().
Fetching 10 files: 100%|███████████████████████████████████████████████████████████████████████| 10/10 [00:00<?, ?it/s]
Loading safetensors

(omnigen) S:\AI-Tools\omnigen>

[staoxiao]

Hi, @Archer7x , is there any error messages? It's difficult to identify the issue with the current information.

[Archer7x]

Hi @staoxiao,
I know its difficult but this is all i have:
it says "Loading safetensors" and then quits to cmd input. I guess it didnt download the model yet. Because I can not find it anywhere. Where should the file model.safetensors be located in the folderstruckture?
The webui gradio is showing up but after pressing generate the app quit.

[staoxiao]

The progress bar shows that the model download is complete, and it will be stored in the default HF_HUB_CACHE. You can try printing this path with the following code:

import os
os.getenv('HF_HUB_CACHE')

You can try to run the model by the code instead of app.py:

from OmniGen import OmniGenPipeline

pipe = OmniGenPipeline.from_pretrained("Shitao/OmniGen-v1")  
# Note: Your local model path is also acceptable, such as 'pipe = OmniGenPipeline.from_pretrained(your_local_model_path)', where all files in your_local_model_path should be organized as https://huggingface.co/Shitao/OmniGen-v1/tree/main

## Text to Image
images = pipe(
    prompt="A curly-haired man in a red shirt is drinking tea.", 
    height=1024, 
    width=1024, 
    guidance_scale=2.5,
    seed=0,
)
images[0].save("example_t2i.png")  # save output PIL Image

[Archer7x]

Same result. I also tried using ComfyUi, but same result. No error, just quit. And I cant find any .safetensors file. Neither in the OmniGen folder nor in the conda omnigen env.

ComfyUI Node

[SyGen899]

having the same issue, no error message just kills the process and goes back to the cmd line. Model files were present in the hub cache folder, so thats not the cause of the issue.