Stable Diffusion 3 Medium (Image to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.

Run SDXL at the speed of light

Anime finetune of Würstchen V3.

Generate short video clips from your images using SVD v1.1 at Lightning Speed

luma-photon

Generate images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.

Predict poses from images.

SD 1.5 ControlNet

SOTA Image Upscaler

Dreamshaper model.

Collection of SDXL Lightning models.

Any pose, any style, any identity

State-of-the-art open-source model in aesthetic quality

Generate realistic images.

High quality zero-shot personalization

Run Any Stable Diffusion model with customizable LoRA weights.

Run Any Stable Diffusion model with customizable LoRA weights.

Run SDXL at the speed of light

Run SDXL at the speed of light

Stable Diffusion v1.5

SDXL with an alpha channel.

Run SDXL at the speed of light

Upscale your images with AuraSR.

MuseTalk is a real-time high quality audio-driven lip-syncing model. Use MuseTalk to animate a face with your own audio.

Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation