✋ This model is not published yet.

You can claim this model if you're @crowsonkb on GitHub. Contact us.

crowsonkb / v-diffusion-jax

text2image with v objective diffusion

  • Public
  • 55 runs
  • T4
  • GitHub
  • Paper
  • License

v-diffusion-jax

v objective diffusion inference code for JAX, by Katherine Crowson (@RiversHaveWings) and Chainbreakers AI (@jd_pressman).

The models are denoising diffusion probabilistic models (https://arxiv.org/abs/2006.11239), which are trained to reverse a gradual noising process, allowing the models to generate samples from the learned data distributions starting from random noise. DDIM-style deterministic sampling (https://arxiv.org/abs/2010.02502) is also supported. The models are also trained on continuous timesteps. They use the ‘v’ objective from Progressive Distillation for Fast Sampling of Diffusion Models (https://openreview.net/forum?id=TIdIXIpzhoI).

Thank you to Google’s TPU Research Cloud and stability.ai for compute to train these models!