sourceactiveLocal models and model tooling Image generation Evaluation and media provenance

THUDM/ImageReward

by @veyrul-import · operator Veyrul founder operations (declared) · founder · revision 2 · updated 2026-10-18 · src_01M569CRJHDJK3K76M26J4JZ90

Evidence: review revision unknown · inspection metadata_checked · execution not_run · review unreviewed · origin research_agent

Source: https://github.com/zai-org/imagereward

L07 2026-10-17: canonical URL updated from https://github.com/THUDM/ImageReward (GitHub redirect to https://github.com/zai-org/ImageReward). L07 2026-10-17: merged duplicate records from lane-d:zai-org--imagereward (same canonical URL).

Structured fields

{
  "archived": false,
  "checked_at": "2026-10-17T00:00:00.000Z",
  "usefulness": "Human-preference reward model for text-to-image outputs (NeurIPS 2023) with scoring, ranking and ReFL fine-tuning. Automatic ranking of candidate generations; measures preference/alignment, not identity consistency.",
  "source_type": "repository",
  "availability": "available",
  "next_check_at": "2026-10-31T00:00:00.000Z",
  "known_limitations": [
    "A single scalar preference score; README names a successor (VisionReward) whose page was not fetched.",
    "Preference scores encode annotator taste; domain shift on film/design imagery untested."
  ],
  "upstream_updated_at": "2025-10-29T13:40:51.000Z"
}

Evidence claims

[upstream_claim] README: first general-purpose text-to-image human-preference reward model, trained on 137k expert comparison pairs, paper arXiv:2304.05977 (NeurIPS 2023); includes ReFL fine-tuning and a Stable Diffusion Web UI scoring script. source
[upstream_claim] README points to a successor, VisionReward, released 2024/12/31; pip install image-reward then RM.load('ImageReward-v1.0') and model.score(prompt, images). source
[upstream_claim] README: first general-purpose text-to-image human preference reward model trained on 137k expert comparison pairs, reported to outperform CLIP, Aesthetic and BLIP scoring; ReFL tuning wins 58.4% against untuned Stable Diffusion in human evaluation (upstream claims). · locator: README intro source
[sourced_fact] Repo now at zai-org/ImageReward (earlier path THUDM/ImageReward returned a redirect via GitHub API); Apache-2.0, not archived, last push 2025-10-29; HF model THUDM/ImageReward tagged apache-2.0. · locator: GitHub API fields; HF API tags source
[upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.

Rights

component	license	hosting	redistribution	modification	training	Evidence and notes
code	Apache-2.0	permitted	permitted	permitted	unknown	https://github.com/THUDM/ImageReward Repository page states Apache-2.0.
dataset	unknown	unknown	unknown	unknown	unknown	https://github.com/THUDM/ImageReward ImageRewardDB license not checked.
model_weights	unknown	unknown	unknown	unknown	unknown	ImageReward-v1.0 model weights license not checked.

Linked records

Machine-readable: JSON · Markdown · revisions · changes