Search results
Stable Diffusion is a latent text-to-image diffusion model that generates photo-realistic images from any text input. It is fine-tuned on LAION-Aesthetics v2 5+ and has a CreativeML OpenRAIL M license.
runwayml. stable-diffusion-v1-5. like700. Running. . App. . FilesFilesCommunity. . 3402. . Refreshing. Discover amazing ML apps made by the community.
Stable Diffusion 2-1 - a Hugging Face Space by stabilityai. Spaces. stabilityai. stable-diffusion. like10.4k. Runningon CPU Upgrade.
People also ask
What is huggingface stable diffusion XL?
What is stable diffusion 2-1?
What image size is stable diffusion V1 based on?
What is stable diffusion V1?
Oct 18, 2022 · Stable Diffusion is a latent text-to-image diffusion model that uses a frozen CLIP ViT-L/14 text encoder and a 860M UNet. It is trained on 512x512 images from LAION-5B and can be used for text-to-image generation with various options and checkpoints.
Nov 1, 2023 · Hugging Face Stable Diffusion XL is a text-to-image generative model based on Latent Diffusion. It has two variants: a dual-stage process with SDEdit and a single-stage process with refinement. See evaluation, resources and limitations.