CLIP Guided latent k-diffusion
Generate images from text using CLIP guided latent diffusion
Generate images using a variety of techniques - Powered by Discoart
Real-ESRGAN with optional face correction and adjustable upscale
Artistic Radiance Fields - Transfer the style of an image to a 3D scene (NeRF)
Upscale images with the latent diffusion superresolution model
Text-to-video generation
Visualize the encoded latents of an image
This model is not yet booted but ready for API calls. Your first API call will boot the model and may take longer, but after that subsequent responses will be fast.
This model runs on T4.
