@replicate

–

06 December 2022 17h16

If you used the mask option, use this model: https://
replicate.com/stablility-ai/
stable-diffusion-inpainting
…

Stable Diffusion img2img and inpainting models separated

By

–

06 December 2022 17h16

img2img and inpainting have moved to two separate models. If you used the init_image option on Stable Diffusion 1.5, you now want to use this model: https://
replicate.com/stablility-ai/
stable-diffusion-img2img
…

New Text Encoder Requires Prompt Experimentation for Different Outputs

By

–

06 December 2022 17h16

The new text encoder means you're going to get different outputs, so you might need to experiment with different prompts.

Stable Diffusion 2.0 launches on Replicate with enhanced capabilities

By

–

06 December 2022 17h16

Stable Diffusion 2.0 is now on Replicate. It has a completely new text encoder developed by @laion_ai and can natively generate images at 768×768 pixels. https://
replicate.com/stability-ai/s
table-diffusion
…

Image Segmentation Models That Return JSON Format

By

–

05 December 2022 16h44

ah, that model's not maintained by us. there are some image segmentation models that return JSON though e.g.

5 December 2022

Stable Diffusion Release Notes Now Available for Version Tracking

By

–

03 December 2022 3h27

Stable Diffusion now has release notes so you can see what's changed: https://
replicate.com/stability-ai/s
table-diffusion/versions
… It just works on Stable Diffusion at the moment. Coming soon to all models so you can set release notes on your own models and see what has changed on other people's models.

3 December 2022

Demo Day: AI Drawing Game and Holiday Art Generator

By

–

02 December 2022 15h30

Spend an hour at Demo Day today with us, @BA_Wolf
, and @JasperSchoormns
. We’ll be demo’ing an AI-powered drawing game, a holiday art generator, and more. Join our Discord to be a part of it at 10AM PT/1PM ET/7PM CET:

2 December 2022

Join AssemblyAI Hackathon December 9th with Replicate GPUs

By

–

29 November 2022 22h29

Come join us at the @AssemblyAI Hackathon on December 9th. They’ve got some big prizes, and we’ll give you some GPUs.

29 November 2022

Current Limitations of Image Output Sizes and Scheduler Options

By

–

24 November 2022 23h27

It doesn't yet support a few things. It only outputs 512 and 768 sized images, doesn't support init_image or mask, and it only has Euler and DDIM schedulers.