Everything on Hugging Face
2 mentions, newest first.
Hugging Face Inference Providers now routes through OpenRouter
Hugging Face Inference Providers switched from its own router to OpenRouter's. Language-model requests go to the provider with the best live mix of price, speed and reliability, and are retried on another provider if one fails. The router supports OpenAI's Chat Completions and Responses APIs and Anthropic's Messages API for every chat model.
Usable todayHugging Face publishes a LoRA fine-tuning guide for the TRELLIS.2 3D model
Hugging Face provides fine-tuning scripts and containers for LoRA fine-tuning of TRELLIS.2 on your own 3D assets, run locally with Docker or on Hugging Face Jobs using the PEFT library. The experiment used 188 footwear objects from Google Scanned Objects; the pretrained model usually made correct-looking shoes with incorrect soles.
Usable today