stability-sdk VS diffusers

I use stable diffusion via stability.ai.

SDXL 0.9 is now available on the Clipdrop by Stability AI platform. Stability AI API and DreamStudio customers will be able to access the model this Monday, 26th June as well as other leading image generating tools like NightCafe.

And for your imaging purposes, you might explore things such as the new StableStudio that Stability AI has. Here's an article about StableStudio. Here are imaging things you can do in StableStudio via its API.

I know there are tons are programs out there but I've made some really cool stuff with this free one https://beta.dreamstudio.ai then rotoscoped it onto a green screen then animated it

Currently Midjourney is the best one, but you need to pay. For low to no cost you could use https://app.leonardo.ai/ or https://beta.dreamstudio.ai/

https://beta.dreamstudio.ai/ (belaj bildoj)

> Of course new SD models are also on the horizon…

SDXL is available at https://beta.dreamstudio.ai/ though they say they're going to release more variants.

I think ControlNet is a lot more interesting than just "better tuned models"; it means there's no line between creating something yourself and asking an AI to do it anymore.

(this is actually generated using the new sdxl beta model in https://beta.dreamstudio.ai )

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