Compositional T2I Generation Diffusion Models

Tools for enhancing spatial reasoning, multi-concept composition, and fine-grained control in text-to-image diffusion models through architectural improvements and guidance techniques. Does NOT include general T2I generation, LoRA training, or personalization fine-tuning methods.

There are 133 compositional t2i generation models tracked. 3 score above 50 (established tier). The highest-rated is PaddlePaddle/PaddleMIX at 60/100 with 718 stars. 2 of the top 10 are actively maintained.

Get all 133 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=diffusion&subcategory=compositional-t2i-generation&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Model	Score	Tier	Stars	Language
1	PaddlePaddle/PaddleMIX Paddle Multimodal Integration and eXploration, supporting mainstream...	60	Established	718	Python
2	UCSC-VLAA/story-iter [ICLR 2026] A Training-free Iterative Framework for Long Story Visualization	58	Established	949	Python
3	keivalya/mini-vla a minimal, beginner-friendly VLA to show how robot policies can fuse images,...	53	Established	204	Python
4	adobe-research/custom-diffusion Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)	44	Emerging	1,971	Python
5	byliutao/1Prompt1Story 🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent...	42	Emerging	313	Python
6	HorizonWind2004/reconstruction-alignment [ICLR 2026] Official repo of paper "Reconstruction Alignment Improves...	42	Emerging	378	Python
7	mit-han-lab/lpd [ICLR 2026 Oral] Locality-aware Parallel Decoding for Efficient...	41	Emerging	91	Python
8	zai-org/ImageReward [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for...	41	Emerging	1,649	Python
9	OpenDriveLab/Nexus [ICCV 2025] Nexus: Decoupled Diffusion Sparks Adaptive Scene Generation	40	Emerging	109	Python
10	JyChen9811/FaithDiff [CVPR 2025] FaithDiff for Classic Film Rejuvenation, Old Photo Revival,...	40	Emerging	240	Python
11	foivospar/Arc2Face [ECCV 2024 Oral 🔥] Arc2Face: A Foundation Model for ID-Consistent Human...	40	Emerging	789	Python
12	ziqihuangg/Collaborative-Diffusion [CVPR 2023] Collaborative Diffusion	40	Emerging	438	Python
13	haoyangzheng-ai/didi-instruct [ICLR 2026] Discrete Diffusion Divergence Instruct (DiDi-Instruct)	39	Emerging	153	Python
14	H-EmbodVis/MERGE [NeurIPS 2025] More Than Generation: Unifying Generation and Depth...	38	Emerging	215	Python
15	lmxyy/sige [NeurIPS 2022, T-PAMI 2023] Efficient Spatially Sparse Inference for...	38	Emerging	268	Python
16	grigorisg9gr/polynomial_nets Official Implementation of the CVPR'20 paper 'Π-nets: Deep Polynomial Neural...	37	Emerging	176	Python
17	yandex-research/swd [ICLR'2026] Scale-wise Distillation of Diffusion Models	37	Emerging	117	Python
18	YixunLiang/UniTEX Official implementation of "UniTEX: Universal High Fidelity Generative...	37	Emerging	172	Python
19	ankanbhunia/PIDM Person Image Synthesis via Denoising Diffusion Model (CVPR 2023)	37	Emerging	500	Jupyter Notebook
20	bytedance/UNO [ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and...	37	Emerging	1,353	Python
21	energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch [ECCV 2022] Compositional Generation using Diffusion Models	36	Emerging	485	Jupyter Notebook
22	yuval-alaluf/Attend-and-Excite Official Implementation for "Attend-and-Excite: Attention-Based Semantic...	36	Emerging	767	Jupyter Notebook
23	junkunyuan/NexusAlign A unified and extensible framework for aligning foundation models.	36	Emerging	2	Python
24	gudaochangsheng/RefAlign Official PyTorch implementation of RefAlign: Representation Alignment for...	36	Emerging	6	Python
25	open-mmlab/PIA [CVPR 2024] PIA, your Personalized Image Animator. Animate your images by...	36	Emerging	978	Python
26	sihyun-yu/REPA [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion...	35	Emerging	1,582	Python
27	WindVChen/Diff-Harmonization A novel zero-shot image harmonization method based on Diffusion Model Prior.	35	Emerging	147	Python
28	youngwanLEE/sdxl-koala [NeurIPS 2024] Empirical Lessons Toward Memory-Efficient and Fast Diffusion...	35	Emerging	147	Python
29	AlaaLab/InstructCV [ ICLR 2024 ] Official Codebase for "InstructCV: Instruction-Tuned...	34	Emerging	461	Python
30	ExplainableML/ReNO [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through...	34	Emerging	166	Python
31	limuloo/MIGC [CVPR 2024 Highlight] MIGC and [TPAMI 2024] MIGC++ (Official Implementation)	34	Emerging	615	Python
32	nupurkmr9/concept-ablation Ablating Concepts in Text-to-Image Diffusion Models (ICCV 2023)	34	Emerging	168	Python
33	gojasper/flash-diffusion ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few...	33	Emerging	657	Python
34	Ammmob/PixelSmile PixelSmile: Fine-grained facial expression editing with continuous control,...	33	Emerging	63	Python
35	HVision-NKU/ImageCritic Official implementation of ImageCritic (CVPR 2026)	32	Emerging	156	Python
36	M-E-AGI-Lab/PSAlign Official Implementation of "PSAlign: Personalized Safety Alignment for...	32	Emerging	7	Python
37	lzyhha/VisualCloze [ICCV 2025] VisualCloze: A universal image generation framework that can...	32	Emerging	279	Python
38	CVL-UESTC/Internal-Guidance CVPR 2026-Guiding a Diffusion Transformer with the Internal Dynamics of Itself (IG)	32	Emerging	60	Python
39	HKUST-LongGroup/Coarse-guided-Gen [arXiv 2026] Official PyTorch Repository for "Coarse-Guided Visual...	32	Emerging	35	Python
40	baojudezeze/RMP-Adapter The implementation of RMP-Adapter: A region-based Multiple Prompt Adapter...	32	Emerging	20	Python
41	NeuralTextualInversion/NeTI Official Implementation for "A Neural Space-Time Representation for...	31	Emerging	181	Python
42	blurgyy/CoMPaSS [ICCV 2025] Enhancing spatial understanding in text-to-Image diffusion models	31	Emerging	92	Python
43	zhiyichin/P4D [ICML 2024] Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models...	30	Emerging	52	Python
44	kfirgoldberg/ConceptLab Official Implementation for "ConceptLab: Creative Generation using Diffusion...	30	Emerging	255	Python
45	RockeyCoss/SPO [CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic...	30	Emerging	265	Python
46	muzishen/IMAGPose [NeurIPS 2024] 🕺IMAGPose🕺: A Unified Conditional Framework for Pose-Guided...	30	Emerging	349	Python
47	ashutosh1919/mdp-diffusion Text-guided image editing by manipulating diffusion path without any training.	30	Emerging	16	Python
48	huanngzh/Parts2Whole [TIP 2025] From Parts to Whole: A Unified Reference Framework for...	30	Emerging	196	Python
49	aminK8/KnobGen CVPR 2025 Workshop on CVEU.	30	Emerging	42	Python
50	VinAIResearch/DiMSUM DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method...	30	Emerging	43	Python
51	sled-group/CycleNet [NeurIPS 2023] Official Code for CycleNet: Rethinking Cycle Consistent in...	30	Emerging	96	Python
52	universome/alis [ICCV 2021] Aligning Latent and Image Spaces to Connect the Unconnectable	29	Experimental	262	Jupyter Notebook
53	LiyaoJiang1998/RAISE "RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free...	29	Experimental	9	Python
54	AIDC-AI/TeEFusion TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance (ICCV 2025)	29	Experimental	9	Python
55	YangLing0818/IterComp [ICLR 2025] IterComp: Iterative Composition-Aware Feedback Learning from...	29	Experimental	204	Python
56	JIA-Lab-research/RIVAL [NeurIPS 2023 Spotlight] Real-World Image Variation by Aligning Diffusion...	29	Experimental	153	Python
57	xie-lab-ml/CoRe2 [TPAMI] The official implementation of our paper "CoRe^2: Collect, Reflect...	29	Experimental	31	Python
58	customdiffusion360/custom-diffusion360 CustomDiffusion360: Customizing Text-to-Image Diffusion with Camera Viewpoint Control	29	Experimental	171	Python
59	boschresearch/Divide-and-Bind Official implementation of "Divide & Bind Your Attention for Improved...	28	Experimental	37	Jupyter Notebook
60	tgxs002/align_sd Better Aligning Text-to-Image Models with Human Preference. ICCV 2023	28	Experimental	294	Python
61	yuxin-jiang/Anomagic [AAAI 2026] The Official Implementation for "Anomagic: Crossmodal...	28	Experimental	129	Python
62	ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization An Pytorch implementation of the paper Key-Locked Rank One Editing for...	28	Experimental	85	Python
63	bytedance-fanqie-ai/MOSAIC [ICLR 2026]🔥🔥🔥MOSAIC: Multi-Subject Personalized Generation via...	28	Experimental	396	Python
64	Nikolai10/PerCo PyTorch implementation of PerCo (Towards Image Compression with Perfect...	27	Experimental	103	Python
65	ChenWu98/generative-visual-prompt [NeurIPS 2022] (Amortized) distributional control for pre-trained generative models	27	Experimental	121	Python
66	VAST-AI-Research/SeqTex [SIGGRAPH Asia 2025] Official github repo of SeqTex, an end-to-end 3D...	27	Experimental	41	Python
67	guillaumejs2403/TIME Text-to-Image Models for Counterfactual Explanations: a black-box approach...	27	Experimental	9	Python
68	mapooon/Face2Diffusion [CVPR 2024] Face2Diffusion for Fast and Editable Face Personalization...	27	Experimental	97	Jupyter Notebook
69	joanrod/figure-diffusion Generating figures from research papers, using textual captions from the paper.	27	Experimental	42	Python
70	TsingZ0/FedKTL CVPR 2024 accepted paper, An Upload-Efficient Scheme for Transferring...	26	Experimental	66	Python
71	kongzhecn/OMG [ECCV 2024] OMG: Occlusion-friendly Personalized Multi-concept Generation In...	26	Experimental	701	Python
72	ChenWu98/unified-generative-zoo [ICCV 2023] https://arxiv.org/abs/2210.05559	26	Experimental	122	Python
73	quickgrid/text-to-image-diffusion Experimental (working!) custom implementation of conditional and...	26	Experimental	5	Python
74	ewrfcas/LeftRefill LeftRefill: Filling Right Canvas based on Left Reference through Generalized...	26	Experimental	82	Python
75	hu-zijing/AsynDM [ICLR 26] Asynchronous diffusion models allocate individual pixels with...	26	Experimental	18	Python
76	opendilab/PRG [ICCV 2025] Pretrained Reversible Generation as Unsupervised Visual...	26	Experimental	28	Python
77	thecrazymage/CasTex [WACV 2026] CasTex: Cascaded Text-to-Texture Synthesis via Explicit Texture...	26	Experimental	33	Python
78	IBM/DiffuseKronA DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized...	25	Experimental	132	Python
79	SPRIGHT-T2I/SPRIGHT [ECCV 2024] Official PyTorch implementation of "Getting it Right: Improving...	25	Experimental	103	Python
80	mofayezi/RobuText [CVPRW 2023] Official implementation of "Benchmarking Robustness to...	24	Experimental	3	Python
81	Raghuram-Veeramallu/DiffTransBEV BEV Representation of an Autonomous car using 6 RGB cameras by making use of...	24	Experimental	4	Python
82	zelaki/ReDi [NeurIPS'25 Spotlight] Boosting Generative Image Modeling via Joint...	24	Experimental	115	Python
83	Nithin-GK/UniteandConquer [CVPR '23] Unite and Conquer: Plug & Play Multi-Modal Synthesis using...	24	Experimental	36	Python
84	haoningwu3639/MegaFusion [WACV 2025] MegaFusion: Extend Diffusion Models towards Higher-resolution...	24	Experimental	99	Python
85	pyladiesams/personalization-with-text-to-image-diffusion-models-feb2024 Get familiar with different fine-tuning techniques for text-to-image models,...	24	Experimental	16	Jupyter Notebook
86	AIDC-AI/CHATS CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for...	24	Experimental	114	Python
87	p-lambda/composed_finetuning Code for the ICML 2021 paper "Composed Fine-Tuning: Freezing Pre-Trained...	24	Experimental	4	Python
88	dsshim0125/s2p "S2P: State-conditioned Image Synthesis for Data Augmentation in Offline...	24	Experimental	4	Python
89	DeepakSridhar/fgdm [NeurIPS 2024] Factor Graph Diffusion Models for Improved Prompt Alignment,...	24	Experimental	2	Python
90	Nithin-GK/MaxFusion [ECCV'24] MaxFusion: Plug & Play multimodal generation in text to image...	23	Experimental	27	Jupyter Notebook
91	rabiulcste/vismin [NeurIPS24] VisMin: Visual Minimal-Change Understanding	23	Experimental	19	Python
92	showlab/BoxDiff [ICCV 2023] BoxDiff: Text-to-Image Synthesis with Training-Free...	23	Experimental	275	Python
93	youweiliang/RichHF Code for CVPR'24 best paper: Rich Human Feedback for Text-to-Image...	22	Experimental	31	Python
94	koi953215/NaRCan [NeurIPS 2024] NaRCan: Natural Refined Canonical Image with Integration of...	22	Experimental	169	Python
95	JortVincenti/DMoE-VAR Research code for the Dynamic Mixture-of-Experts in Visual Autoregressive...	22	Experimental	—	Python
96	wateasca/DiffusionVL 🌟 Translate autoregressive models into cutting-edge diffusion vision...	22	Experimental	—	Python
97	sooyeon-go/eye_for_an_eye Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Models	21	Experimental	32	Jupyter Notebook
98	alibaba/mm-diff MM-Diff: High-Fidelity Image Personalization via Multi-Modal Condition Integration	20	Experimental	27	Python
99	Ka1b0/Foresight-Guidance NeurIPS25 Spotlight \| Classifier-free guidance (CFG) can be viewed as...	20	Experimental	9	Python
100	bytedance/ID-Patch Official implementation of CVPR 2025 paper "ID-Patch: Robust ID Association...	20	Experimental	75	Python
101	lxa9867/ControlVAR This is the official implementation for ControlVAR.	20	Experimental	126	Python
102	johndpope/Emote-hack Emote Portrait Alive - using ai to reverse engineer code from white paper....	20	Experimental	184	Python
103	byliutao/Cradle2Cane （NeurIPS 2025) From Cradle to Cane: A Two-Pass Framework for High-Fidelity...	20	Experimental	7	Python
104	yandex-research/adaptive-diffusion [CVPR'2024] Adaptive Teacher-Student Collaboration for Text-Conditional...	20	Experimental	33	Python
105	ConceptBed/evaluations [AAAI 2024] ConceptBed Evaluations for Personalized Text-to-Image Diffusion Models	20	Experimental	25	Python
106	tuananhbui89/Embedding-Adjustment Mitigating Semantic Collapse in Generative Personalization with Test-Time...	19	Experimental	10	Jupyter Notebook
107	yugwangyeol/Facial-caricature-profile-GIF [Project] Facial-caricature-profile GIF	18	Experimental	4	Python
108	YangLing0818/ContextDiff [ICLR 2024] Contextualized Diffusion Models for Text-Guided Image and Video...	18	Experimental	73	Python
109	Viresh-R/ml-CCA Implementation of Fast ml-CCA from the ICCV-2015 work "Multi-Label...	18	Experimental	22	Matlab
110	CFGpp-diffusion/CFGpp Official repository for "CFG++: manifold-constrained classifier free...	18	Experimental	238	Python
111	muzishen/RCDMs [AAAI 2025] 🎬RCDMs🎬: Boosting Consistency in Story Visualization with...	18	Experimental	120	Python
112	hohonu-vicml/DirectedDiffusion Directed Diffusion: Direct Control of Object Placement through Attention...	18	Experimental	81	Python
113	RuiqingYoung/EAR Learning to Expand Images for Efficient Visual Autoregressive Modeling	18	Experimental	4	Python
114	sungnyun/diffblender DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion Models	17	Experimental	46	Python
115	diaoenmao/Multimodal-Controller-for-Generative-Models [CVMI 2022] Multimodal Controller for Generative Models	16	Experimental	3	Python
116	PeterHUistyping/M3ashy M^3ashy: Multi-Modal Material Synthesis via Hyperdiffusion, AAAI'26 (former...	16	Experimental	1	Python
117	basiclab/MAD MAD: Makeup All-in-One with Cross-Domain Diffusion Model	16	Experimental	31	Python
118	YangLing0818/RealCompo [NeurIPS 2024] RealCompo: Balancing Realism and Compositionality Improves...	16	Experimental	121	Python
119	abyildirim/md-projtex Text-guided 3D texture generation using training-free multi-diffusion in UV space.	16	Experimental	14	—
120	nanlliu/Unsupervised-Compositional-Concepts-Discovery [ICCV 2023] Unsupervised Compositional Concepts Discovery with Text-to-Image...	16	Experimental	85	Python
121	ZiyiZhang27/MVC-ZigAL [CVPR 2026] Code for the paper "Refining Few-Step Text-to-Multiview...	16	Experimental	9	Python
122	dt-3t/LSRS Official PyTorch implementation of "LSRS: Latent Scale Rejection Sampling...	15	Experimental	—	Python
123	wfanyue/DPG-T2I-Personalization [ECCV 2024] Powerful and Flexible: Personalized Text-to-Image Generation via...	14	Experimental	51	Python
124	james-oldfield/PoS-subspaces [NeurIPS'23] Parts of Speech–Grounded Subspaces in Vision-Language Models	14	Experimental	29	Jupyter Notebook
125	agneet42/revision [ECCV 2024] "REVISION: Rendering Tools Enable Spatial Fidelity in...	14	Experimental	13	Python
126	play-with-HOI-generation/HOIG [NeurIPS 2022 Spotlight] Hand-Object Interaction Image Generation	14	Experimental	33	Python
127	X-GenGroup/PaCo-RL Official Implementation for *PaCo-RL: Advancing Reinforcement Learning for...	14	Experimental	32	Python
128	SHI-Labs/Diffusion-Driven-Test-Time-Adaptation-via-Synthetic-Domain-Alignment Everything to the Synthetic: Diffusion-driven Test-time Adaptation via...	14	Experimental	40	Python
129	quickgrid/paper-implementations Attempts to implement various deep learning, computer vision papers.	12	Experimental	4	Jupyter Notebook
130	TsinghuaC3I/Efficient-Diffusion-Models TPAMI 2025 Survey Paper	12	Experimental	26	Python
131	anhquanpham/iterative-comp-rl-generation Iterative Compositional Data Generation for Robot Control	11	Experimental	5	Python
132	jiuntian/OneHOI [CVPR2026] Official repo for "OneHOI: Unifying Human-Object Interaction...	11	Experimental	—	—
133	rese1f/pose2img pose-driven human natural image generation based on latent diffusion model	10	Experimental	1	Jupyter Notebook

Comparisons in this category

story-iter and 1Prompt1Story (58 vs 42)