- cross-posted to:
- fosai@lemmy.world
- cross-posted to:
- fosai@lemmy.world
SDXL-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation. A real-time demo is available here: http://clipdrop.co/stable-diffusion-turbo
Key Takeaways:
-
SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one.
-
See our research paper for specific technical details regarding the model’s new distillation technique that leverages a combination of adversarial training and score distillation.
-
Download the model weights and code on Hugging Face, currently being released under a non-commercial research license that permits personal, non-commercial use.
-
Test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities
Model weights and code: https://huggingface.co/stabilityai/sdxl-turbo
Demo: https://clipdrop.co/stable-diffusion-turbo
Paper: https://stability.ai/research/stability-ai-adversarial-diffusion-distillation
You must log in or register to comment.
This will be awesome for something like the Krita plugin where you want almost instant generation.
This is being released under a non-commercial research license for now. I hope they open source it soon.
Here is an alternative Piped link(s):
https://piped.video/adDyTzBdUcg
Piped is a privacy-respecting open-source alternative frontend to YouTube.
I’m open-source; check me out at GitHub.
deleted by creator
