G-U-N/Phased-Consistency-Model
A NeurIPS 2024 generative image model that boosts consistency models for fast, high-quality image synthesis.
Not currently ranked — collecting fresh signals.
star history
Phased Consistency Models (PCM) is a diffusion-model-based image generation approach that improves the performance of consistency models. It supports integration with Stable Diffusion 3 and Stable Diffusion XL via LoRA adapters, providing deterministic and stochastic sampling modes for few-step image generation. The project releases training scripts, pretrained weights on Hugging Face, and demo spaces.
Frequently asked
- What is G-U-N/Phased-Consistency-Model?
- A NeurIPS 2024 generative image model that boosts consistency models for fast, high-quality image synthesis.
- Is Phased-Consistency-Model open source?
- Yes — G-U-N/Phased-Consistency-Model is open source, released under the Apache-2.0 license.
- What language is Phased-Consistency-Model written in?
- G-U-N/Phased-Consistency-Model is primarily written in Python.
- How popular is Phased-Consistency-Model?
- G-U-N/Phased-Consistency-Model has 520 stars on GitHub.
- Where can I find Phased-Consistency-Model?
- G-U-N/Phased-Consistency-Model is on GitHub at https://github.com/G-U-N/Phased-Consistency-Model.