Excited to submit to the '23 DreamBooth Hackathon at huggingface
Stable diffusion is an extremely revolutionary and popular text-to-image foundation model used to generate realistic images.
If you have a Hugging Face account - plz check out the link above and like it, would be awesome to win!
If you don’t have an account it is very quick to make one!
About Stable Diffusion
Stable diffusion is an extremely revolutionary and popular text-to-image foundation model used to generate realistic images. Applications like Lens.ai are generating millions of dollars a month acting as simple UX wrappers on top of Stable Diffusion, creating custom, guided, and fine-tuned output for users looking to create exciting and beautiful Avatars.
Stable Diffusion works by tokenizing english language words (using CLIP) and iteratively applying input weights to latent space, in a way that gradually bringing the output closer to the input prompt.
- A key benefit of stable diffusion is that it can be fine-tuned to generate high-quality images with a simple and open-source text2image model.
Applications like http://Lens.ai are generating $$$ by simply acting as simple UX wrapper to facilitate the process of creating exciting and beautiful Avatars. Check out my Collab Notebook for a step-by-step process on fine-tuning here: https://colab.research.google.com/drive/1EnqpDiKOVYhR0c6f4CgmDg2zqcbYZJpB#scrollTo=a22e8a3e-620e-4dff-8cea-3732003c17fa
From my example submission:
For this hackathon submission, we have fine tuned a model to create scenic landscapes of golf-courses, with historic and mythological buildings in the background.
It’s using a small 21 image dataset (that’s stored on the decentralized edge, on Storj DCS, that’s used to fine-tune the underlying stable diffusion model.
Goal is to replicate this with much larger datasets and showcase the use case pattern for data training models (ie LAION-5B) in future.