Lnyan

Results 50 comments of Lnyan

> > > > > > > > > `from_pretrained` is a method of `StableDiffusionPipeline` > > ``` > > text2img = StableDiffusionPipeline.from_pretrained( > > "path_to_model_folder", > > revision="fp16", >...

> > @arpitest I have ported the canvas interaction to frontend via pyscript and gradio. The colab version should work without lags now. @fractaltr33 Erasing is also implemented with the...

> If you are getting black square, most likely it's NSFW image. You can try to change your prompt and try! @x18-1 The false positive rate of `safety checker`/`NSFW detector`...

> @lkwq007 > > I try ,but it didn’t work ![image](https://user-images.githubusercontent.com/1665437/193854293-f020d8d2-dff5-4e6c-b721-8198a27430f5.png)

> I too have a GTX 1660 Ti. At first I had the same issue in Stable Diffusion from Automatic 1111; however, after I forced FULL PRECISION via CMD LINE...

You need to accept the license agreement to access the model weights: https://huggingface.co/runwayml/stable-diffusion-inpainting

> Undo erasing, if I erase part of the image and try to outpaint there and I don't like the result, I need to be able to undo what I've...

`python app.py` should be executed inside the stablediffusion-infinity folder

- go to the stablediffusion-infinity directory with Explorer - open powershell with file menu - `conda activate sd-inf` - `python app.py`