Shypd.aiThe largest open index of AI toolsDiffusionDPO is an open-source coding and development tool that provides training code for aligning diffusion models. It enables researchers and developers to implement direct preference optimization for models like StableDiffusion1.5 and StableDiffusion-XL-1.0.
Trending
About
DiffusionDPO is a code repository from SalesforceAIResearch, offering the training code for "Diffusion Model Alignment Using Direct Preference Optimization." This tool is designed for researchers and developers working with diffusion models, providing scripts adapted from the diffusers library. It supports the alignment of models such as StableDiffusion1.5 and StableDiffusion-XL-1.0, with examples for running training on these models. The repository includes utilities for scoring models using various AI feedback mechanisms like PickScore, HPS, Aesthetics, and CLIP, along with notebooks for visualizing results and comparing generations. It's a valuable resource for those looking to fine-tune and evaluate diffusion models for specific preferences.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
