Running
on
CPU Upgrade
462
πͺπͺ©
LoRA Studio
Browse and run thousands of community trained LoRAs
Dominus Zeikyu
DominusZeikyu1998
Β·
AI & ML interests
AI
Recent Activity
liked
a Space
6 days ago
enzostvs/lora-studio
Organizations
None yet
DominusZeikyu1998's activity
liked
a
Space
6 days ago
liked
a
Space
4 months ago
liked
a
Space
7 months ago
reacted to
akhaliq's
post with π
7 months ago
Post
20596
Phased Consistency Model
Phased Consistency Model (2405.18407)
The consistency model (CM) has recently made significant progress in accelerating the generation of diffusion models. However, its application to high-resolution, text-conditioned image generation in the latent space (a.k.a., LCM) remains unsatisfactory. In this paper, we identify three key flaws in the current design of LCM. We investigate the reasons behind these limitations and propose the Phased Consistency Model (PCM), which generalizes the design space and addresses all identified limitations. Our evaluations demonstrate that PCM significantly outperforms LCM across 1--16 step generation settings. While PCM is specifically designed for multi-step refinement, it achieves even superior or comparable 1-step generation results to previously state-of-the-art specifically designed 1-step methods. Furthermore, we show that PCM's methodology is versatile and applicable to video generation, enabling us to train the state-of-the-art few-step text-to-video generator.
Phased Consistency Model (2405.18407)
The consistency model (CM) has recently made significant progress in accelerating the generation of diffusion models. However, its application to high-resolution, text-conditioned image generation in the latent space (a.k.a., LCM) remains unsatisfactory. In this paper, we identify three key flaws in the current design of LCM. We investigate the reasons behind these limitations and propose the Phased Consistency Model (PCM), which generalizes the design space and addresses all identified limitations. Our evaluations demonstrate that PCM significantly outperforms LCM across 1--16 step generation settings. While PCM is specifically designed for multi-step refinement, it achieves even superior or comparable 1-step generation results to previously state-of-the-art specifically designed 1-step methods. Furthermore, we show that PCM's methodology is versatile and applicable to video generation, enabling us to train the state-of-the-art few-step text-to-video generator.
Connection errored out
2
#15 opened 7 months ago
by
ikkyu90
liked
3
Spaces
7 months ago
liked
a
model
7 months ago
liked
a
Space
9 months ago
liked
2
models
over 1 year ago
liked
a
Space
over 1 year ago
liked
3
models
over 1 year ago
liked
a
Space
over 1 year ago
liked
2
datasets
almost 2 years ago