facebookresearch / capiLinks
Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
☆113Updated 3 months ago
Alternatives and similar repositories for capi
Users that are interested in capi are comparing it to the libraries listed below
Sorting:
- WIP☆93Updated 11 months ago
- ☆102Updated 3 months ago
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆176Updated last year
- ☆34Updated 2 months ago
- Train VAE like a boss☆287Updated 9 months ago
- 🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…☆82Updated 7 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆274Updated 2 weeks ago
- Focused on fast experimentation and simplicity☆76Updated 7 months ago
- ☆21Updated 9 months ago
- My take on Flow Matching☆69Updated 6 months ago
- ☆293Updated 3 months ago
- Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).☆168Updated 3 months ago
- ☆83Updated last year
- FlexTok: Resampling Images into 1D Token Sequences of Flexible Length☆234Updated 2 months ago
- Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. TMLR 2025.☆88Updated 2 months ago
- ☆53Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆130Updated last year
- ☆51Updated last year
- Synthetic Alphabet Dataset☆19Updated 4 months ago
- ConceptAttention: A method for interpreting multi-modal diffusion transformers.☆314Updated 3 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆288Updated 2 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆94Updated last week
- Implementations of attention with the softpick function, naive and FlashAttention-2☆81Updated 3 months ago
- Implementation of a multimodal diffusion transformer in Pytorch☆102Updated last year
- ☆23Updated last year
- Clarity: A Minimalist Website Template for AI Research☆130Updated 6 months ago
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆55Updated 2 months ago
- VIT inference in triton because, why not?☆31Updated last year
- Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"☆129Updated 6 months ago
- Scalable and Performant Data Loading☆290Updated last week