Alternatives and similar repositories for InstructG2I

Users that are interested in InstructG2I are comparing it to the libraries listed below

• zhangxulu1996 / Compositional-Inversion
  Compositional Inversion for Stable Diffusion Models (AAAI 2024)
  ☆36Updated 5 months ago
• hutaiHang / ATM
  ☆25Updated 3 months ago
• daeunni / VideoRepair
  Code for "VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement"
  ☆49Updated 8 months ago
• showlab / D-AR
  the official repo for "D-AR: Diffusion via Autoregressive Models"
  ☆110Updated last month
• YangLing0818 / EditWorld
  [ACM Multimedia 2025 Datasets Track] EditWorld: Simulating World Dynamics for Instruction-Following Image Editing
  ☆131Updated last week
• KAIST-Visual-AI-Group / Flow-Inference-Time-Scaling
  Official code for Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
  ☆61Updated last month
• G-U-N / Diffusion-NPO
  [ICLR 2025] official implementation of "Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffu…
  ☆25Updated 2 weeks ago
• jacklishufan / Reflect-DiT
  Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection
  ☆45Updated 3 weeks ago
• xie-lab-ml / Zigzag-Diffusion-Sampling
  [ICLR2025] The code of Z-Sampling, proposed in our paper "Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflectio…
  ☆81Updated 5 months ago
• FlowChef / FlowChef
  [ICCV 2025] Official Implementation of Steering Rectified Flow Models in the Vector Field for Controlled Image Generation
  ☆33Updated last month
• jylei16 / Imagine-e
  ☆11Updated 6 months ago
• KwonGihyun / TweedieMix
  Official source codes of "TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation" (ICLR 2025)
  ☆54Updated 6 months ago
• Adamdad / vico
  Vico: Compositional Video Generation as Flow Equalization
  ☆58Updated 8 months ago
• YangLing0818 / ContextDiff
  [ICLR 2024] Contextualized Diffusion Models for Text-Guided Image and Video Generation
  ☆69Updated last year
• mlvlab / DeepVideoR1
  ☆20Updated last month
• Young98CN / LoRA_Composer
  LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models
  ☆64Updated 11 months ago
• ZhenglinZhou / DreamDPO
  [ICML 2025] DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization
  ☆15Updated 2 months ago
• aniki-ly / FreeLong
  [NeurIPS 2024] The official implement of research paper "FreeLong : Training-Free Long Video Generation with SpectralBlend Temporal Atten…
  ☆55Updated last month
• Monalissaa / DisenDiff
  [CVPR`2024, Oral] Attention Calibration for Disentangled Text-to-Image Personalization
  ☆104Updated last year
• SilentView / EMCID
  Official Implementation for "Editing Massive Concepts in Text-to-Image Diffusion Models"
  ☆19Updated last year
• superolly / self-guidance
  Unofficial implementation of "Diffusion Self-Guidance for Controllable Image Generation" (Epstein et al., 2023)
  ☆32Updated 2 years ago
• BIGKnight / Understanding-Training-free-Diffusion-Guidance
  ☆17Updated last year
• weixi-feng / TC-Bench
  ☆24Updated last year
• YangLing0818 / RealCompo
  [NeurIPS 2024] RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
  ☆117Updated 8 months ago
• KaiyueSun98 / T2V-CompBench
  [CVPR 2025] T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation
  ☆90Updated 2 months ago
• arthur-qiu / FreeTraj
  Code for FreeTraj, a tuning-free method for trajectory-controllable video generation
  ☆104Updated last year
• yhZhai / mcm
  [NeurIPS 2024] Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation
  ☆66Updated 9 months ago
• Jialuo-Li / Science-T2I
  [CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis
  ☆59Updated 3 months ago
• Xiang-cd / unet-finetune
  fixed official code for paper "A Closer Look at Parameter-Efficient Tuning in Diffusion Models".
  ☆41Updated 2 years ago
• measure-infinity / mulan-code
  ☆41Updated last year