Two random LoRAs are loaded into SDXL, can you find a way to combine them?

GitHub: https://github.com/kakaobrain/karlo

diffusers lib integration: https://github.com/huggingface/diffusers/releases/tag/v0.11....

Probably the cheapest UI, by hacking a bit Hugging Face Spaces. Also works locally. Of course Google Colab is still free but I think the UI / pre-curation of hyperparameters may be worth it?

Pipelines also load faster, more schedulers are out, and the community contributed a bunch!

Which is fairer imo than paying for the whole site. I prefer creator control on which content is paid and which content is not.

Hi, I'm the creator of multimodal.art, I didn't overlook it, but there's no "specialized" NSFW content maker to be highlighted - this Vice articles just show people using the model in different iterations to generate NSFW content; you don't need a specialized notebook/tool for that, a few ones on the post can do it (others have a NSFW filter that comes in by default).

Additionally it is important to note that model was licensed under the OpenRAIL-M LICENSE which is not as permissive as an MIT license and forbids certain outputs to be shared or purposes to be built as apps

I thought only the "derivatives of the model" are under the user restrictions in the license, and are very permissive. The outputs of the model are very briefly covered in the license text

> You are accountable for the Output you generate and its subsequent uses. No use of the output can contravene any provision as stated in the License.

>there's no "specialized" NSFW content maker to be highlighted

Unless I'm misunderstanding you, yes there is, and it was even posted on HN last week:

https://news.ycombinator.com/item?id=32572770

(And yes, many of its results are horrifying)

Goes without saying, but enthusiasts are working on it and making progress. Here's a quote from a discussion on it yesterday:

as far as I am aware, I may have the only semi-tuned nsfw model, though it's not all that great. There are a lot of concepts that SD needs to learn, and they're difficult to teach. It's very likely that by the time I get something usable, it's going to destroy all of the other concepts. @<another_user> also has a fine tuned model, but it's only tuned on generating closeups of female genitals. If that's all you want to generate, then he's produced some really good results. As for distribution, I wouldn't know where to begin, considering the model is 11GB

No, this is just Stable Diffusion without any modification, no fine-tuning is needed to create nudes.

Stable diffusion trained on a nude-free data set might struggle somewhat.

Hi everyone! I am the creator of this website multimodal.art. Our goal is to break the barries of entry for this tech, as well as to inform people about the potentil of that technology. We also developed MindsEye, an open source pilot to many AI art models (VQGAN+CLIP, Guided Diffusion and Latent Diffusion) https://multimodal.art/mindseye

Who else read the title and though it would render photo realistic glasses as filters in your face? :-)