The authors started from two pretrained text-to-image pixel diffusion models, DeCo and PixelGen, which generate RGB images directly instead of via a latent code.
Adversarial post-training fixes high-frequency deficit in pixel diffusion models
Adding an adversarial loss to pretrained pixel diffusion generators improves fidelity, coverage, and prompt alignment without altering architecture or sampling.
Independent
Xin Lin · Zhifei Zhang · Yuqian Zhou · Haitian Zheng · Zhe Lin · Ming-Hsuan Yang · +1 more
Research Digest··3 min read
Lin et al.
Why this paper
Independent
In one line
Adversarial post-training improves pixel diffusion outputs by restoring missing high-frequency image statistics.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§