BREAKING
NeMo AutoModel Adds Diffusers Support
Fine-Tuning for Image and Video
Launch Model Recipes
Text-to-ImageFLUX.1-dev
12B parameters
Full and LoRA recipes
Text-to-VideoWan 2.1
1.3B parameters
HunyuanVideo 1.5 too
The Fine-Tuning Workflow
1Load HF model
2Encode VAE latents
3FSDP2 training
4Generate & infer
0x
min throughput
0x
max throughput
0%
memory cut
A Standardized Fine-Tuning Path
AI NEWS BLITZ
NVIDIA expands its open-source NeMo AutoModel library to Hugging Face Diffusers.