fal-ai / diffusion-speedrun
Focused on fast experimentation and simplicity
☆65Updated last month
Alternatives and similar repositories for diffusion-speedrun:
Users that are interested in diffusion-speedrun are comparing it to the libraries listed below
- supporting pytorch FSDP for optimizers☆76Updated 2 months ago
- ☆21Updated 8 months ago
- WIP☆93Updated 6 months ago
- ☆26Updated 9 months ago
- ☆30Updated 4 months ago
- ☆25Updated 8 months ago
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆86Updated this week
- ☆43Updated last month
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆122Updated 10 months ago
- ☆24Updated 2 months ago
- ☆32Updated 3 months ago
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆73Updated 6 months ago
- ☆33Updated 5 months ago
- ☆75Updated 7 months ago
- A JAX implementation of the continuous time formulation of Consistency Models☆84Updated last year
- My take on Flow Matching☆37Updated last month
- ☆51Updated last year
- realtime latent world model inference demo☆42Updated 3 months ago
- Recaption large (Web)Datasets with vllm and save the artifacts.☆44Updated 2 months ago
- Train VAE like a boss☆265Updated 3 months ago
- Latent Diffusion Language Models☆68Updated last year
- Implementation of Diffusion Transformers and Rectified Flow in Jax☆21Updated 7 months ago
- σ-GPT: A New Approach to Autoregressive Models☆61Updated 6 months ago
- ☆53Updated last year
- Efficient optimizers☆169Updated this week
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆73Updated this week
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆118Updated 5 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆86Updated 3 months ago