huggingface/finetrainers
Scalable and memory-optimized training of diffusion models
Supports distributed training via DDP, FSDP-2, and HSDP, plus LoRA and full-rank fine-tuning across multiple video generation models (LTX-Video, CogVideoX, HunyuanVideo, Wan) and image models (Flux, CogView4). Built on the Diffusers framework with pluggable attention backends (flash, flex, xformers) and enables FP8 quantization-aware training to reduce VRAM requirements for single-GPU and large-scale scenarios.
1,343 stars. No commits in the last 6 months.
Stars
1,343
Forks
140
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/huggingface/finetrainers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVlabs/Sana
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
FoundationVision/VAR
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈]...
nerdyrodent/VQGAN-CLIP
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
eps696/aphantasia
CLIP + FFT/DWT/RGB = text to image/video
AssemblyAI-Community/MinImagen
MinImagen: A minimal implementation of the Imagen text-to-image model