A pose control extension developed based on the BRIA 2.3 text-to-image model, generating high-quality images through text prompts and human pose estimation from input images

Computer VisionDiffusers

A ControlNet extension developed based on the BRIA 2.3 text-to-image model, enabling color style control through color grids

Computer VisionDiffusers

A ControlNet background generation model developed based on the BRIA 2.3 text-to-image model, capable of generating high-quality images through text prompts and background masks

Computer VisionDiffusers

A ControlNet extension developed based on the BRIA 2.3 text-to-image model, enabling image color reset and diverse variant generation through text prompts and grayscale guidance

Computer VisionDiffusers

BRIA 2.3 ControlNet-Canny is a ControlNet version developed based on the BRIA 2.3 text-to-image model, capable of generating high-quality images through text prompts and input image edge maps.

Computer VisionDiffusers

BRIA 2.3 Fast Edition is the LCM-accelerated version of BRIA 2.3, representing the best balance between quality and speed in the 2.X series. This model is trained on legally compliant data, perfectly combining technological innovation with ethical responsibility and legal safeguards.

Computer VisionDiffusers

BRIA 2.3 is a text-to-image model trained on legally compliant datasets, integrating technological innovation with ethical responsibility and legal safeguards, setting a new benchmark for the AI industry.

Computer VisionDiffusers

InternLM-20B is a 20-billion-parameter pretrained model jointly released by Shanghai AI Laboratory, SenseTime, The Chinese University of Hong Kong, and Fudan University. Pretrained on over 2.3T high-quality Chinese-English and code token data, it demonstrates outstanding comprehensive performance and powerful tool-calling capabilities.

Natural Language ProcessingTransformers

A QA model fine-tuned on SQuAD v1 based on BERT-base uncased, with 66% of linear layer weights pruned via nn_pruning library, achieving 2.32x inference speedup

Natural Language ProcessingTransformersEnglish