OPEN SOURCE

–

12 July 2023 12h59

In April, we also launched the first of our StableLM Suite of language models. Newer models are on their way!

DeepFloyd IF: Advanced Text-to-Image Generation Model Released

By

–

12 July 2023 12h59

Stable Diffusion models aren't our only text-to-image models. The @deepfloydai team worked hard to train and publicly release DeepFloyd IF, a state-of-the-art image generation model that is better at text and photorealism:

Stable Diffusion V2.1 Released with Enhanced Training

By

–

12 July 2023 12h59

Just a couple weeks later, Stable Diffusion V2.1 was released, which was trained for longer on more data!

Stable Diffusion 2.0 Released with Inpainting and Super-Resolution

By

–

12 July 2023 12h59

We followed that up shortly with the release of Stable Diffusion 2.0, which also came with a suite of models for inpaintining. depth-to-image, and super-resolution!

→ View original post on X — @googleai

ArchGym: Open-Source Gymnasium for ML-Assisted Architecture Design

By

@googleai

–

11 July 2023 19h48

Check out ArchGym, an open-source gymnasium that 1) connects a range of search algorithms to computer architecture simulators, 2) facilitates research in ML-assisted computer architecture design & 3) forms the scaffold to develop reproducible baselines → https://t.co/scu4CiNpld pic.twitter.com/VYBdCfTc8n
— Google AI (@GoogleAI) 11 juillet 2023

Check out ArchGym, an open-source gymnasium that 1) connects a range of search algorithms to computer architecture simulators, 2) facilitates research in ML-assisted computer architecture design & 3) forms the scaffold to develop reproducible baselines → https://
goo.gle/3JPcRSo

→ View original post on X — @_akhaliq

Hugging Face Papers Daily Email Distribution Announcement

By

@_akhaliq

–

11 July 2023 16h17

https://
huggingface.co/papers daily email just went out

→ View original post on X — @mustafasuleyman

AI frontier meets open source innovation in months

By

@mustafasuleyman

–

11 July 2023 14h43

Never has the distance between the absolute technical frontier and everyday open source innovation been smaller. It's now a matter of months… The coming wave of AI is truly remarkable.

→ View original post on X — @_akhaliq

AnimateDiff: Animate Personalized Text-to-Image Diffusion Models

By

@_akhaliq

–

11 July 2023 5h42

AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

paper page: https://t.co/0GkcW9l1cP

With the advance of text-to-image models (e.g., Stable Diffusion) and corresponding personalization techniques such as DreamBooth and LoRA, everyone… pic.twitter.com/4nfCKyUXO3
— AK (@_akhaliq) 11 juillet 2023

AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning paper page: https://
huggingface.co/papers/2307.04
725
… With the advance of text-to-image models (e.g., Stable Diffusion) and corresponding personalization techniques such as DreamBooth and LoRA, everyone

→ View original post on X — @h2oai

h2oGPT Demo: Future of Open Source AI

By

@h2oai

–

11 July 2023 5h23

We are back with yet another demo video, this time helping you to dive into the Future of #OpenSource AI with #h2oGPT! h2oGPT is a fully permissive Apache V2 open-source project for 100% private and secure use of LLMs. https://
youtube.com/watch?v=Gx1TDr
HFABo&feature=youtu.be#AI
…