Papers with Code · CC BY-SA 4.0

GenEval

아카이브 평가 20건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
SD3.5-Medium+Flow-GRPO	Overall 0.95	Flow-GRPO: Training Flow Matching Models via Online RL 2025-05-08	코드 1
UniWorld-V1 (Rewrite)	Single Obj. 0.98 Two Obj. 0.93 Counting 0.81 Colors 0.90 Position 0.74 Color Attri. 0.71 Overall 0.84	UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation 2025-06-03	코드 1 · 코드 2
MindOmni	Single Obj. 0.99 Two Obj. 0.94 Counting 0.71 Colors 0.90 Position 0.71 Color Attri. 0.71 Overall 0.83	MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO 2025-05-19	코드 1
UniWorld-V1	Single Obj. 0.99 Two Obj. 0.93 Counting 0.79 Colors 0.89 Position 0.49 Color Attri. 0.70 Overall 0.80	UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation 2025-06-03	코드 1 · 코드 2
SANA-1.5 4.8B (+ Inference Scaling)	Overall 0.80	SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer 2025-01-30	코드 1
Janus-Pro-7B	Overall 0.80	Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling 2025-01-29	코드 1
MetaQuery-XL (Rewrite)	Overall 0.80	Transfer between Modalities with MetaQueries 2025-04-08	연결 없음
Show-o [xie2024show] PARM It. DPO PARM	Overall 0.77	Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step 2025-01-23	코드 1 · 코드 2
Show-o [xie2024show] Ft. ORM It. DPO Ft. ORM	Overall 0.75	Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step 2025-01-23	코드 1 · 코드 2
Janus-Pro-1B	Overall 0.73	Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling 2025-01-29	코드 1
Lumina-Image 2.0	Overall 0.73	Lumina-Image 2.0: A Unified and Efficient Image Generative Framework 2025-03-27	코드 1
SANA-1.5 4.8B	Single Obj. 0.99 Two Obj. 0.85 Overall 0.72	SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer 2025-01-30	코드 1
Fluid (10.5B)	Single Obj. 0.96 Two Obj. 0.83 Counting 0.63 Colors 0.80 Position 0.39 Color Attri. 0.51 Overall 0.69	Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens 2024-10-17	코드 1
Und. and Gen. Show-o (Ours)	Overall 0.68	Show-o: One Single Transformer to Unify Multimodal Understanding and Generation 2024-08-22	코드 1
Emu3	Overall 0.66	Emu3: Next-Token Prediction is All You Need 2024-09-27	코드 1 · 코드 2
SnapGen	Overall 0.66	SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training 2024-12-12	연결 없음
JanusFlow	Overall 0.63	JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation 2024-11-12	코드 1
PixArt-Σ	Overall 0.53	PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation 2024-03-07	코드 1 · 코드 2
DiffMoE-E16-T2I-Flow (w SFT)	Overall 0.51	DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers 2025-03-18	연결 없음
PIXART-δ	Overall 0	PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models 2024-01-10	코드 1