New Stable Diffusion Latent Upscaler Explained - 2X Upscale in Seconds

Описание

Latent diffusion-based upscaler developed by Katherine Crowson in collaboration with Stability AI. This model was trained on a high-resolution subset of the LAION-2B dataset. It is a diffusion model that operates in the same latent space as the Stable Diffusion model, which is decoded into a full-resolution image. To use it with Stable Diffusion, You can take the generated latent from Stable Diffusion and pass it into the upscaler before decoding with your standard VAE. Or you can take any image, encode it into the latent space, use the upscaler, and decode it.

Note: This upscaling model is designed explicitely for Stable Diffusion as it can upscale Stable Diffusion's latent denoised image embeddings. This allows for very fast text-to-image + upscaling pipelines as all intermeditate states can be kept on GPU. More for information, see example below. This model works on all Stable Diffusion checkpoints

Works on any stable diffusion models - https://huggingface.co/models?other=stable-diffusion

Stable Diffusion x2 Latent Upscaler - https://huggingface.co/stabilityai/sd-x2-latent-upscaler

Google Colab - https://colab.research.google.com/drive/1MLpJUc87b9Xpx1JLlOOGVYF9g8o5ULp8?usp=sharing

❤️ If you want to support what we are doing ❤️
Support here:
Patreon - https://www.patreon.com/1littlecoder/
Ko-Fi - https://ko-fi.com/1littlecoder