⚡ Flash Diffusion: FlashSD3 ⚡

This is an interactive demo of Flash Diffusion, a diffusion distillation method proposed in Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation by Clément Chadebec, Onur Tasar, Eyal Benaroche and Benjamin Aubin from Jasper Research. This model is a 90.4M LoRA distilled version of SD3 model that is able to generate 1024x1024 images in 4 to 8 steps. Results can be compared with the teacher model here. Currently running on GPU.

If you enjoy the space, please also promote open-source by giving a ⭐ to the Github Repo.

💡 Hint: We noticed that 8 steps and CFG can improve the results (text rendering in particular) for that very model. Feel free to play with those parameters.

💡 Hint: To better appreciate the low latency of our method, run the demo locally !

Disclaimer:

This demo is only for research purpose. Jasper cannot be held responsible for the generation of NSFW (Not Safe For Work) content through the use of this demo. Users are solely responsible for any content they create, and it is their obligation to ensure that it adheres to appropriate and ethical standards. Jasper provides the tools, but the responsibility for their use lies with the individual user.