vipermu

hey hn! I'm one of the founders at Krea.

we prepared a blogpost about how we trained FLUX Krea if you're interested in learning more: https://www.krea.ai/blog/flux-krea-open-source-release

hey hn! I'm one of the founders at Krea.

we prepared a blogpost about how we trained FLUX Krea if you're interested in learning more: https://www.krea.ai/blog/flux-krea-open-source-release

exactly

how will this change with ai though?

it would be interesting to play with LCM-LoRAs and AnimateDiff and see how much much this technique can speed up video generation.

not sure if it's possible to just plug-and-play it or if we would need an extra LCM-LoRA for the motion module.

once we have these sort of models producing frames in milliseconds we should be able to do something similar to this demo but with videos.

indeed; we're able to make it work with SDXL thanks to a new technique that got released yesterday called LCM-LoRA.

with LCM-LoRA you can turn models like SDXL into LCMs without need for training and you can add other style LoRAs like the ones you find on civit.ai

in case you're interested, here's the technical report about LCM-LoRA: https://arxiv.org/abs/2311.05556

it uses a new technique called "consistency" that lets latent diffusion models to predict images in much fewer steps.

some links here: - https://arxiv.org/abs/2310.04378 - https://arxiv.org/abs/2311.05556

Here's a brief explanation of ControlNet, a new method that can be used to control large diffusion models in arbitrary conditions, such as image edges, human poses, or segmentation maps.

really cool! that must have been a lot of work. Here's another great site for references: https://proximacentaurib.notion.site/proximacentaurib/parrot...

Good question. All the generations in the dataset were generated with version 1.3.

yup! btw, if you want compressed generators you'll enjoy this discussion https://discuss.huggingface.co/t/decoding-latents-to-rgb-wit...

in krea.ai you can create collections of images with their prompts by pressing the "+" button in an image.

you also have access to all the different components that create each prompt, and you can search similar ones by clicking them.

Stable Diffusion was released just a month ago and look at the amount of applications and improvements that have been developed, it feels like a year!

Open-source is the way to get the most out of this tech. We plan to keep building all the features that are to come at krea.ai in this way.

We're living some crazy times! A truly AI summer.

If you enjoy thinking about how the future of this field might look like, I highly recommend watching the interview between Yannic Kilcher and Sebastian Risi (https://www.youtube.com/watch?v=_7xpGve9QEE).

I was mind-blown after hearing it. It was a long time since I didn't hear such an interesting conversation. It's crazy how Risi's ideas correlate so well with the way how complex systems emerge in nature (optimizing locally), and the idea of self-organizing systems is just amazing.

You can use the code in https://github.com/krea-ai/prompt-search to do so. You first want to compute the CLIP embeddings of each prompt, index them using something like K-Nearest Neighbors (so you can get search for similarities fast), and then, given an input prompt, you will be able to find other indexed prompts that share their semantics.

fixed!

thanks for spotting the issue :)

Thanks! Great work with Lexica.

We also released a free API https://devapi.krea.ai/ if anyone wants to check it out.

It will soon have endpoints with custom image generation features.

Thanks! Prompts can be hard to create, we hope that having access to these kinds of datasets we will be able to create tools and conduct studies that help us create better images and understand better the possibilities of AI models like stable diffusion.

I wonder how CLIP search would work for finding errors in the dataset.

For now, a workaround is to create your own "glitch" collection in krea.ai and store there images with artifacts.

If you end up doing it we will add a "download all" button right away :)

And all the prompts from each collection could also be added to Open Prompts for sure.

The source (Stability AI Discord) is the same, but I don't know how Sharif gathered his data.

We do not have a continuous system, the data is a mix between our own crawled generations and the dataset published by Dave Caruso (https://github.com/paperdave). With our crawler, we were able to get about 100k generations per day.

you should check out these amazing art studies by @proximasan, @EErratica, @KyrickYoung, and @sureailabs (twitter) https://proximacentaurib.notion.site/proximacentaurib/parrot...

Just wrote this article introducing the main ideas on why Transformers can be so powerful for Computer Vision applications. Hope you find it insightful, any feedback is welcome :)