facebookresearch / EvalGIMLinks
π¦Ύ EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic evaluations of text-to-image models and supports customization with user-defined metrics, datasets, and visualizations.
β82Updated 7 months ago
Alternatives and similar repositories for EvalGIM
Users that are interested in EvalGIM are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] Source code for paper "A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrβ¦β76Updated 7 months ago
- A one-stop library to standardize the inference and evaluation of all the conditional image generation models. [ICLR 2024]β170Updated 3 months ago
- Inference-time scaling of diffusion-based image and video generation models.β161Updated last month
- β62Updated this week
- [CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesisβ113Updated 2 months ago
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationβ143Updated 6 months ago
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).β79Updated last year
- Minimal Differentiable Image Reward Functionsβ79Updated 2 weeks ago
- UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, aβ¦β112Updated 4 months ago
- (ICCV 2025) "Principal Components" Enable A New Language of Imagesβ54Updated last week
- Official Implementation of weights2weightsβ147Updated 4 months ago
- β86Updated last year
- FlexTok: Resampling Images into 1D Token Sequences of Flexible Lengthβ234Updated 2 months ago
- [ICLR 2025] Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stitβ¦β103Updated last year
- Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?β126Updated 5 months ago
- Official PyTorch implementation of TokenSet.β121Updated 4 months ago
- A Video Tokenizer Evaluation Datasetβ129Updated 6 months ago
- The official PyTorch implementation for Improving Long-Text Alignment for Text-to-Image Diffusion Models (LongAlign)β76Updated 3 months ago
- Sparse Autoencoders for Stable Diffusion XL models.β69Updated last week
- Davidsonian Scene Graph (DSG) for Text-to-Image Evaluation (ICLR 2024)β91Updated 7 months ago
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sampβ¦β294Updated 9 months ago
- β174Updated 2 years ago
- Official implementation of the paper The Hidden Language of Diffusion Modelsβ74Updated last year
- (CVPR 2024) π§© TokenCompose: Text-to-Image Diffusion with Token-level Supervisionβ126Updated 7 months ago
- [ICCV 2023] Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Modelsβ84Updated last year
- Simple large-scale training of stable diffusion with multi-node support.β133Updated 2 years ago
- [ICML 2025] This is the official repository of our paper "What If We Recaption Billions of Web Images with LLaMA-3 ?"β138Updated last year
- [IJCV 2025] Paragraph-to-Image Generation with Information-Enriched Diffusion Modelβ105Updated 4 months ago
- TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringβ170Updated last year
- [NeurIPS 2024] Official PyTorch Implementation of "FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner"β71Updated 10 months ago