Image Generation on WISE

15개 결과 · ⬇ CSV · JSON

Overall

Rank	Model	Overall	Cultural	Time	Space	Biology	Physics	Chemistry	Paper	Code	Year
1	MindOmni (w/ cot)	0.71	0.75	0.70	0.76	0.76	0.72	0.52	MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO	easonxiao-888/mindomni	2025
2	Bagel (w/ cot)	0.70	0.76	0.69	0.75	0.65	0.75	0.58	Emerging Properties in Unified Multimodal Pretraining	ByteDance-Seed/Bagel · neverbiasu/ComfyUI-BAGEL	2025
3	MetaQuery-XL	0.55	0.56	0.55	0.62	0.49	0.63	0.41
3	UniWorld-V1	0.55	0.53	0.55	0.73	0.45	0.59	0.41	UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation	PKU-YuanGroup/UniWorld-V1 · pku-yuangroup/imgedit	2025
5	Bagel	0.52	0.44	0.55	0.68	0.44	0.60	0.39	Emerging Properties in Unified Multimodal Pretraining	ByteDance-Seed/Bagel · neverbiasu/ComfyUI-BAGEL	2025
6	Playground-v2.5-1024px-aesthetic	0.49	0.49	0.58	0.55	0.43	0.48	0.33	Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation		2024
7	PixArt-XL-2-1024-MS	0.47	0.45	0.50	0.48	0.49	0.56	0.34	PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis	PixArt-alpha/PixArt-alpha · Karine-Huang/T2I-CompBench · swookey-thinky/image_diffusion	2023
8	stable-diffusion-3.5-large	0.46	0.44	0.50	0.58	0.44	0.52	0.31	Scaling Rectified Flow Transformers for High-Resolution Image Synthesis	Karine-Huang/T2I-CompBench · hxixixh/adaflow	2024
9	stable-diffusion-xl-base-0.9	0.43	0.43	0.48	0.47	0.44	0.45	0.27	SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis	stability-ai/generative-models · compvis/fm-boosting · yuchen413/text2image_safety · +6	2023
9	MindOmni (w/o cot)	0.43	0.40	0.38	0.62	0.36	0.52	0.32	MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO	easonxiao-888/mindomni	2025
11	Emu3-gen	0.39	0.34	0.45	0.48	0.41	0.45	0.27	Emu3: Next-Token Prediction is All You Need	baaivision/emu3 · flagopen/flagscale	2024
12	Janus-pro	0.35	0.30	0.37	0.49	0.36	0.42	0.26	Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling	deepseek-ai/janus	2025
12	Show-o	0.35	0.28	0.40	0.48	0.30	0.46	0.30	Show-o: One Single Transformer to Unify Multimodal Understanding and Generation	showlab/show-o	2024
14	Janus	0.23	0.16	0.26	0.35	0.28	0.30	0.14	Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling	deepseek-ai/janus	2025
15	Mural 자동 추출	–	–	0.66	–	–	–	–	Mural: Transferring LLM knowledge to image generation via Mixture-of-Transformers		2026