OpenCodePapers
text-to-image-generation-on-oneig-zh
Image Generation
Text-to-Image Generation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
OneIG Overall Score
↕
ModelName
ReleaseDate
↕
Qwen-Image Technical Report
✓ Link
0.548
Qwen-Image
2025-08-04
GenRouter: Unified Workflow Routing for Agentic Image Generation
✓ Link
0.545
GenCanvas + GenRouter (Z-Image)
2026-08-17
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
✓ Link
0.540
SenseNova-U1-A3B-MoT
2026-05-12
Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers
✓ Link
0.538
PPCL (Qwen-Image, 14B)
2025-11-20
SenseNova-U1.5: Towards Native Unified Visual Intelligence
✓ Link
0.536
SenseNova-U1.5
2026-09-10
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
✓ Link
0.535
Z-Image
2025-11-27
UniSpace: Unified Visual Representation and Scalable Multimodal Modeling
✓ Link
0.533
UniSpace
2026-08-09
GEMS: Agent-Native Multimodal Generation with Memory and Skills
✓ Link
0.532
GEMS
2026-03-30
Emu3.5: Native Multimodal Models are World Learners
✓ Link
0.529
Emu3.5 (34B)
2025-10-30
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
✓ Link
0.525
Lens
2026-05-20
Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
✓ Link
0.521
JoyAI-Image
2026-05-05
Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
✓ Link
0.52
MrFlow + Qwen-Image (20+1 steps)
2026-07-02
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
✓ Link
0.512
BitDance-14B-16x
2026-02-15
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
✓ Link
0.509
Mage-Flow-Base
2026-07-21
InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
✓ Link
0.5
InternVL-U (4B)
2026-03-10
×