Pith. sign in

REVIEW 7 cited by

Human Preference Score: Better Aligning Text-to-Image Models with Human Preference

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

arxiv 2303.14420 v2 pith:Q7GNXJV4 submitted 2023-03-25 cs.CV cs.AI

classification cs.CVcs.AI
keywords humanmodelsimagespreferencealignchoicesstablebetter
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent years have witnessed a rapid growth of deep generative models, with text-to-image models gaining significant attention from the public. However, existing models often generate images that do not align well with human preferences, such as awkward combinations of limbs and facial expressions. To address this issue, we collect a dataset of human choices on generated images from the Stable Foundation Discord channel. Our experiments demonstrate that current evaluation metrics for generative models do not correlate well with human choices. Thus, we train a human preference classifier with the collected dataset and derive a Human Preference Score (HPS) based on the classifier. Using HPS, we propose a simple yet effective method to adapt Stable Diffusion to better align with human preferences. Our experiments show that HPS outperforms CLIP in predicting human choices and has good generalization capability toward images generated from other models. By tuning Stable Diffusion with the guidance of HPS, the adapted model is able to generate images that are more preferred by human users. The project page is available here: https://tgxs002.github.io/align_sd_web/ .

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Bootstrap Flow-Map Tree Sampling Enables Online Feedback Driven Search

    cs.LG 2026-07 conditional novelty 7.0 of 10

    Bootstrap Flow-Map Trees construct complete DDPM-like trajectories with a single NFE and dynamic steps, enabling efficient online feedback-driven search and alignment that beats prior tree and SMC samplers.

  2. Multi-Turn On-Policy Distillation with Prefix Replay

    cs.LG 2026-07 conditional novelty 6.0 of 10

    ReOPD offline-distills multi-turn agentic LLMs via teacher-prefix replay plus step-decay sampling, matching online OPD accuracy at ≥4× speed with zero tool calls.

  3. Self-Improving Diffusion Classifiers with Minority Preference Optimization

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Fine-tuning a diffusion model with a reconstruction-error minority reward via LoRA+GRPO improves zero-shot diffusion classification by expanding low-density coverage.

  4. Symbolic Graphics Programming with Large Language Models

    cs.CV 2025-09 conditional novelty 6.0 of 10

    Qwen-2.5-7B trained with reinforcement learning against SigLIP visual similarity scores writes SVG drawings that match text captions about as well as frontier models on several automated metrics.

  5. VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment

    cs.CV 2026-03 conditional novelty 5.5 of 10

    A VGGT-based pointwise reprojection reward with geometry-aware sampling improves video geometric consistency via SFT/DPO and causal test-time search.

  6. RewardDance: Reward Scaling in Visual Generation

    cs.CV 2025-09 conditional novelty 5.0 of 10

    RewardDance reframes visual reward modeling as a yes/no judgment task in a VLM and reports consistent gains in text-to-image, text-to-video, and image-to-video generation as the reward model scales from 1B to 26B.

  7. Instant Preference Alignment for Text-to-Image Diffusion Models

    cs.CV 2025-08 conditional novelty 5.0 of 10

    An MLLM-driven, training-free pipeline extracts preference keywords from a reference image and modulates diffusion cross-attention at global and regional levels for instant, multi-round preference-aligned image generation.

Pith tools