CREATIVE AI

Fine-tuning and ControlNet Advances for SDXL Text-to-Image AI

By

–

22 August 2023 18h02

Seeing the fast follow from the community racing to get fine-tuning and ControlNet working for SDXL has been exciting. These techniques bring text-to-image AI to life. Here are some examples of my dog Queso of SD2.1 Dreambooth (left) vs. SDXL LoRA (right). The quality is

Stable Diffusion XL 1.0 Released: Community Discovers Amazing Results

By

–

22 August 2023 18h02

In July 2023, Stable Diffusion XL 1.0 was released. The 1.0 release of SDXL marks a huge leap forward over previous generations. It has only been a few weeks, and the community is still discovering how to make it amazing. So far the results have been stunning.

Stable Diffusion 2: The Awkward Second Album

By

–

22 August 2023 18h02

In October 2022, Stable Diffusion 2 was released. It was sort of like the awkward 2nd album. Good, just… different. The migration to OpenCLIP as the text encoder significantly changed image composition and limited the use of artists' names that could be used in prompts.

Stable Diffusion 1.4 Celebrates One Year Anniversary

By

–

22 August 2023 18h01

On August 22, 2022 (1yr ago today!) Stable Diffusion 1.4 made its debut. Happy Birthday Stable Diffusion! At last, it seemed like it was finally possible to generate consistently good images from a text prompt.

VQGAN and CLIP Notebooks: A Significant Step Forward in Image Generation

By

–

22 August 2023 18h01

In April 2022, @RiversHaveWings shared a series of Colab notebooks that combined VQGAN and CLIP. https://
x.com/RiversHaveWing
s/status/1516582795438567424
… This was a significant step forward. Images were starting to resemble their prompts, and textures like brush strokes and pencil marks were starting to emerge.

Pixray reaches 1.3 million runs on Replicate platform

By

–

22 August 2023 18h01

In early 2022 @dribnet
's Pixray was the first text-to-image model on Replicate to reach thousands of runs. Today it's been run a total of 1.3mil times. @dribnet was actually the first Replicate user to request that we build an API instead of just a web ui. The rest is history

OpenAI’s DALL·E 2 and the Rise of Diffusion Models

By

–

22 August 2023 18h01

In April 2021, OpenAI announced DALL·E 2 https://
openai.com/dall-e-2 and detailed their transition toward using diffusion models. It felt like the dream was coming true! You could prompt it for a photo of a cat wearing a red hat, and get a cat wearing a red hat!

→ View original post on X — @stabilityai

Stable Diffusion Anniversary: One Year of Generative AI Innovation

By

@stabilityai

–

22 August 2023 17h19

One year ago, we co-released @StableDiffusion
! It has enabled countless creative applications over this past year, opening up new possibilities for the future of generative AI. Since then, we've also released 36 models for public access, including SD 2.x, SDXL, StableLM, etc.