Alternatives and similar repositories for IDEA-Bench

Users that are interested in IDEA-Bench are comparing it to the libraries listed below

• hqhQAQ / PatchDPO
  [CVPR 2025] PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
  ☆38Updated 2 weeks ago
• Eureka-Maggie / MIGE
  Implementation code of the paper MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing
  ☆64Updated last month
• ali-vilab / ChatDiT
  ☆50Updated 6 months ago
• QY-H00 / Conceptrol
  Conceptrol: Concept Control of Zero-shot Personalized Image Generation
  ☆39Updated 3 months ago
• WUyinwei-hah / IFAdapter
  [ICCV2025] Official implementation of "IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation".
  ☆57Updated 2 weeks ago
• PRIS-CV / I-Max
  Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers
  ☆52Updated 8 months ago
• yuriYanZeXuan / EEdit
  EEdit⚡: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing
  ☆42Updated 3 months ago
• ML-GSAI / Concat-ID
  Concat-ID: Towards Universal Identity-Preserving Video Synthesis
  ☆54Updated 2 months ago
• OPPO-Mente-Lab / PEA-Diffusion
  PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation
  ☆35Updated 8 months ago
• aim-uofa / FreeCompose
  ☆45Updated 9 months ago
• louisYen / Gen4Gen
  🏞️ Official implementation of "Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition"
  ☆107Updated last year
• CUC-MIPG / Edit-Transfer
  Official code of "Edit Transfer: Learning Image Editing via Vision In-Context Relations"
  ☆80Updated last month
• zhaoshitian / LeX-Art
  Official Implementation of "LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis"
  ☆63Updated 3 months ago
• sooyeon-go / eye_for_an_eye
  Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Models
  ☆28Updated 10 months ago
• Xiaojiu-z / SSR_Encoder
  Pytorch Implementation of "SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation"(CVPR 2024)
  ☆123Updated 11 months ago
• YangLing0818 / RealCompo
  [NeurIPS 2024] RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
  ☆117Updated 8 months ago
• hithqd / DynamicControl
  ☆40Updated 6 months ago
• LingjieKong-fdu / CustAny
  Official code for CustAny: Customizing Anything from A Single Example. Accepted by CVPR2025 (Oral)
  ☆46Updated 3 months ago
• YujiaHu1109 / IEAP
  IEAP: Image Editing As Programs with Diffusion Models
  ☆98Updated last month
• open-mmlab / AnyControl
  [ECCV 2024] AnyControl, a multi-control image synthesis model that supports any combination of user provided control signals. 一个支持用户自由输入控…
  ☆127Updated last year
• TencentARC / BlobCtrl
  [Arxiv'25] BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing
  ☆9Updated 3 months ago
• eclipse-t2i / lambda-eclipse-inference
  [TMLR] Official PyTorch implementation of "λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent…
  ☆51Updated 7 months ago
• Rbrq03 / ClassDiffusion
  [ICLR2025] ClassDiffusion: Official impl. of Paper "ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance"
  ☆42Updated 4 months ago
• alipay / style-tokenizer
  ☆100Updated last year
• feizc / Video-In-Context
  Video Diffusion Transformers are In-Context Learners
  ☆24Updated 6 months ago
• wutong16 / FiVA
  [ NeurIPS 2024 D&B Track ] Implementation for "FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models"
  ☆70Updated 6 months ago
• Yuanshi9815 / Subjects200K
  Subjects200K dataset
  ☆114Updated 5 months ago
• tobran / StoryImager
  [ECCV2024] StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion
  ☆38Updated last year
• ant-research / edicho
  [Arxiv 2024] Edicho: Consistent Image Editing in the Wild
  ☆117Updated 6 months ago
• Nihukat / Concept-Conductor
  ☆15Updated 4 months ago