NVIDIA has expanded its open-source NeMo AutoModel library to support Hugging Face Diffusers, bringing ready-to-run fine-tuning recipes for image- and video-generation models to a tool that previously focused on language models. The move lets developers load pretrained diffusion models directly from the Hugging Face Hub and run distributed fine-tuning—both full and parameter-efficient—without stitching together their own training pipelines.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.