Álvaro Somoza

I'll do the kandinsky special test at the end which is the one failing.

While doing the tests I'm getting an error if I do the test with `StableDiffusionInpaintPipeline` The error happens in this line: https://github.com/huggingface/diffusers/blob/1221b28eac1801dd759e8d1df9fc9a2a998b41ed/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py#L1380 Since the `SDCFGCutoffCallback` makes the `guidance_scale 0.0`, I...

yeah, I'll try to do them all in this PR.

> ohhhh another way is just handle this in the callbacks. I think you can actually combine the SD and SDXL callbacks with if "add_text_embeds" in callback_kwargs: ... Now that...

You should translate your question to English, and even with google translate I don't understand the issue you have. > Integration ControlNet, IPAdapter в pipe StableDiffusionControlNetImg2ImgPipeline There are such input...

HI @Eduard6315, sorry I totally forgot about this issue. Do you still need help or you already found the solution?

ok, I did some tests, when you say nothing comes out you mean that the images generated are black? If that's the problem, that's because fine tuned models generate a...

That repository only has the safetensors checkpoints, you need to use `use_safetensors=True`

hmm so you're saying you manually downloaded the files? In that case you should put the path to where you downloaded the files. Also that proxy doesn't work for me...

When you take into account usability, what @okaris is proposing is the way I thought it should work the first time I used the image-to-image pipeline. Both `comfyui` and `automatic1111`...