Real-ESRGAN with optional face correction and adjustable upscale
Generate images from text using CLIP guided latent diffusion
Generate images using a variety of techniques - Powered by Discoart
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
CLIP Guided latent k-diffusion
Visualize the encoded latents of an image
This model is booted and ready for API calls.
This model runs on T4.
