hustvl/LightningDiT

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1529 stars · 56 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

LightningDiT is a research codebase for latent diffusion models implementing VA-VAE and LightningDiT, achieving FID 1.35 on ImageNet-256 with 21.8x faster training than the original DiT. It accompanies a CVPR 2025 Oral paper on taming the reconstruction-vs-generation optimization dilemma in visual tokenizers.

Use cases

• train a latent diffusion transformer on ImageNet-256
• reproduce state-of-the-art image generation FID results
• train a VA-VAE visual tokenizer
• make diffusion transformer research affordable on few GPUs
• experiment with visual tokenizer latent dimensions
• generate images with pretrained diffusion transformer weights

When to choose

• you need fast, reproducible DiT-style image generation training
• you are researching latent diffusion tokenizers and the reconstruction-generation tradeoff
• you have limited GPU budget but want competitive ImageNet generation results

When to avoid

• you need a production-ready image generation API or product
• you want text-to-image generation on arbitrary prompts rather than class-conditional ImageNet
• you are not working with PyTorch GPU research workflows

Facets

library · maturity active

machine-learning deep-learning image-processing deep-learning machine-learning image-processing computer-vision python latent-diffusion diffusion-transformer vae image-generation research-code cvpr-2025 gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="hustvl/LightningDiT")