REVIEW 8 cited by
Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences
read the original abstract
One-step text-to-image generator models offer advantages such as swift inference efficiency, flexible architectures, and state-of-the-art generation performance. In this paper, we study the problem of aligning one-step generator models with human preferences for the first time. Inspired by the success of reinforcement learning using human feedback (RLHF), we formulate the alignment problem as maximizing expected human reward functions while adding an Integral Kullback-Leibler divergence term to prevent the generator from diverging. By overcoming technical challenges, we introduce Diff-Instruct++ (DI++), the first, fast-converging and image data-free human preference alignment method for one-step text-to-image generators. We also introduce novel theoretical insights, showing that using CFG for diffusion distillation is secretly doing RLHF with DI++. Such an interesting finding brings understanding and potential contributions to future research involving CFG. In the experiment sections, we align both UNet-based and DiT-based one-step generators using DI++, which use the Stable Diffusion 1.5 and the PixelArt-$\alpha$ as the reference diffusion processes. The resulting DiT-based one-step text-to-image model achieves a strong Aesthetic Score of 6.19 and an Image Reward of 1.24 on the COCO validation prompt dataset. It also achieves a leading Human preference Score (HPSv2.0) of 28.48, outperforming other open-sourced models such as Stable Diffusion XL, DMD2, SD-Turbo, as well as PixelArt-$\alpha$. Both theoretical contributions and empirical evidence indicate that DI++ is a strong human-preference alignment approach for one-step text-to-image models. The homepage of the paper is https://github.com/pkulwj1994/diff_instruct_pp.
Forward citations
Cited by 8 Pith papers
-
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
D-OPSD formulates supervised fine-tuning of step-distilled diffusion models as on-policy self-distillation by minimizing distribution differences between a text-only student and a multimodal teacher on the student's o...
-
Reinforcing Few-step Generators via Reward-Tilted Distribution Matching
RTDMD unifies KL minimization to a reward-tilted teacher into distribution matching plus reward terms, using AC-DMD in stage one and hybrid GRPO-style gradients plus SubGRPO in stage two to reach new SOTA on preferenc...
-
Unbiased Diffusion Variational Inversion via Principled Posterior Matching
PPM derives a tractable gradient for exact KL optimization in diffusion variational inversion to achieve unbiased posterior matching without heuristic approximations.
-
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
D-OPSD enables continuous supervised fine-tuning of few-step diffusion models via on-policy self-distillation where the model acts as both teacher (multimodal context) and student (text-only context) on its own roll-outs.
-
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
D-OPSD formulates supervised fine-tuning of step-distilled diffusion models as on-policy self-distillation by having the model act as both teacher (with multimodal context) and student (with text-only context) on its ...
-
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Live Avatar reports real-time streamable generation from a 14B audio-driven diffusion model at ~20 FPS on 5 H800s with stable identity over 10,000 seconds.
-
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Live Avatar enables 45 FPS real-time streaming infinite-length audio-driven avatar generation from a 14B diffusion model via distillation and timestep-forcing pipeline parallelism.
-
Distribution Matching Distillation Meets Reinforcement Learning
Combining DMD distillation with RL during training produces few-step text-to-image models that outperform their multi-step teacher on several benchmarks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.