procreate-diffusion.github.io - ProCreate-Diffusion

home > domains > procreate-diffusion.github.io

Description: DESCRIPTION META TAG

keywords should be placed here (74)

Example domain paragraphs

In this paper, we propose ProCreate, a simple and easy-to-implement method to improve sample diversity and creativity of diffusion-based image generative models and to prevent training data reproduction. ProCreate operates on a set of reference images and actively propels the generated image embedding away from the reference embeddings during the generation process. We propose FSCG-8 (Few-Shot Creative Generation 8), a few-shot creative generation dataset on eight different categories---encompassing differe

At each denoising step of a pre-trained diffusion model, ProCreate applies propulsive guidance that maximizes the distances between the generated clean image and the reference images.

We collect dataset FSCG-8, fine-tune a Stable Diffusion checkpoint on each category of image-caption pairs, and compare the samples generated from DDIM , CADS , and ProCreate.

Links to procreate-diffusion.github.io (2)

• jacklu0831.github.io Jack (Yi Ao) Lu
• jacklu-me.com Jack (Yi Ao) Lu