How to input gradio settings in Python

[levoz92]

Hi.

I use realisticStockPhoto_v20 on Fooocus with sdxl_film_photography_style lora and I really like the results. Fooocus and other gradio implementations come with settings inputs that I want to utilize in Python as well. In particular, if this is my code:

device = "cuda"
model_path = "weights/realisticStockPhoto_v20.safetensors"

pipe = StableDiffusionXLInpaintPipeline.from_single_file(
    model_path, 
    torch_dtype=torch.float16, 
    num_in_channels=4).to(device)

pipe.load_lora_weights(".", weight_name="weights/SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors", adapter_name="film")

how can I set the following settings/parameters in code?

• Negative Prompt
• Preset (initial, lcm, default, lighting, realistic, sai, anime)
• Performance (quality, speed, extreme speed, lightning)
• width-height
• image number
• output format
• Style (Fooocus v2, fooocus photography, fooocus negative, foocus enhance, etc.)
• Base Model
• Refiner
• Lora 1,2,3,4,5,...
• Guidance scale
• Image sharpness

[tolgacangoz]

I strongly recommend you examine the docs page for that pipeline.

[levoz92]

I strongly recommend you examine the docs page for that pipeline.

Definitely will do. Thanks.

But just a cursory overview, I don't see a lot of what I listed in the documentation. Nothing about Preset, Performance, Style, Base, Refiner.

[tolgacangoz]

I think "performance" can be arranged with num_inference_steps and strength. You can search "refiner" in the search bar on the docs page to see all the examples in the diffusers. The styles seem special for Fooocus; they should be adaptable here as well. Idk about preset. A more knowledgeble may answer you.

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.