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 8 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¦β77Updated 8 months ago
- β86Updated last year
- Sparse Autoencoders for Stable Diffusion XL models.β69Updated 3 weeks ago
- β64Updated 3 weeks ago
- UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, aβ¦β118Updated 4 months ago
- A one-stop library to standardize the inference and evaluation of all the conditional image generation models. [ICLR 2024]β171Updated 4 months ago
- [CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesisβ112Updated 3 months ago
- Minimal Differentiable Image Reward Functionsβ82Updated this week
- Official Implementation of weights2weightsβ147Updated 5 months ago
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).β80Updated last year
- [ICML 2025] This is the official repository of our paper "What If We Recaption Billions of Web Images with LLaMA-3 ?"β138Updated last year
- [ICLR 2025] Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stitβ¦β103Updated last year
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationβ145Updated 6 months ago
- Inference-time scaling of diffusion-based image and video generation models.β165Updated last month
- Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?β127Updated 6 months ago
- Official implementation of the paper The Hidden Language of Diffusion Modelsβ74Updated last year
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"β176Updated last year
- (ICCV 2025) "Principal Components" Enable A New Language of Imagesβ58Updated 3 weeks ago
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sampβ¦β297Updated 9 months ago
- NeuMeta transforms neural networks by allowing a single model to adapt on the fly to different sizes, generating the right weights when nβ¦β43Updated 9 months ago
- Davidsonian Scene Graph (DSG) for Text-to-Image Evaluation (ICLR 2024)β92Updated 8 months ago
- Official PyTorch implementation of TokenSet.β121Updated 5 months ago
- A Video Tokenizer Evaluation Datasetβ130Updated 7 months ago
- Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"β148Updated 6 months ago
- β34Updated 3 months ago
- Matryoshka Multimodal Modelsβ113Updated 7 months ago
- Train VAE like a bossβ292Updated 10 months ago
- β50Updated last year
- β105Updated last week
- The official implementation of Diffusion-KTO: Aligning Diffusion Models by Optimizing Human Utilityβ59Updated last week