stable-diffusion VS diffusers

Download this training project: git clone https://github.com/justinpinkney/stable-diffusion.git

looks like it's using the https://github.com/justinpinkney/stable-diffusion/blob/4ac995b6f663b74dfe65400285e193d4167d259c/scripts/gradio_image_mixer.py to do the bulk of the work meaning the core functionality is built into stable diffusion, seems the UI just isn't built to support it. Their ckpt is here too https://huggingface.co/lambdalabs/image-mixer/tree/main.

Any idea how to make Image Mixer work in this build? On RTX 3060 with 12Gb of memory I get the message:

References: ►Read the full article: https://www.louisbouchard.ai/imagic/ ►Kawar, B., Zada, S., Lang, O., Tov, O., Chang, H., Dekel, T., Mosseri, I. and Irani, M., 2022. Imagic: Text-Based Real Image Editing with Diffusion Models. arXiv preprint arXiv:2210.09276. ► Use it with Stable Diffusion: https://github.com/justinpinkney/stable-diffusion/blob/main/notebooks/imagic.ipynb ►My Newsletter (A new AI application explained weekly to your emails!): https://www.louisbouchard.ai/newsletter/

The notebook: https://github.com/justinpinkney/stable-diffusion/blob/main/notebooks/imagic.ipynb

There's a script for the SD --> Diffusers here: https://github.com/justinpinkney/stable-diffusion/blob/main/scripts/convert_sd_to_diffusers.py

You can start with the github which contains the code: https://github.com/justinpinkney/stable-diffusion

Hmmm, I just double checked the hashes of my local file, what's on huggingface, and what you showed above and they all match. I'm not familiar with that repo, so maybe something weird is going on. I tested it using the original txt2img script in the stable diffusion repo:

*PICK\* (Added Sep. 12, 2022) Web app Stable Diffusion Image Variations by lambdalabs. GitHub repo. Generates variations of an input image without use of a text prompt. Censored.

I'm missing something about the random factor, from the sample code from https://github.com/huggingface/diffusers/blob/main/README.md

Hey people, I noticed that combining these two methods in a single forward pass increases the controllability of the generation quite a bit. I was kind of puzzled that sometimes ControlNet yielded better results than T2IAdapter for some cases, and sometimes it was the other way around, so I decided to test both at the same time, and results were quite nice. Some visuals and more motivation here: https://github.com/huggingface/diffusers/issues/5847 And it was already merged here: https://github.com/huggingface/diffusers/pull/5869

Open Parti Prompts: The better way to evaluate diffusion models (repo)

You have disabled the safety checker for by passing `safety_checker=None`. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .

For developers, TensorRT support also exists for the diffusers library via community pipelines. [1] It's limited, but if you're only supporting a subset of features, it can help.

In general, these insane speed boosts comes at the cost of bleeding edge features.

[1] https://github.com/huggingface/diffusers/blob/28e8d1f6ec82a6...

I was training sdxl UNET base model, with the diffusers library, which was going great until around step 210k when the weights suddenly turned back to their original values and stayed that way. I also tried with the ema version, which didn't change at all. I also looked at the tensor's weight values directly which confirmed my suspicions.

Merging LoRAs is essentially taking a weighted average of the LoRA adapter weights. It's more common in other UIs.

diffusers is working on a PR for it: https://github.com/huggingface/diffusers/pull/4473