Research over 2 years ago

Segmind Introduces SegMoE: Mixture of Experts Architecture for Diffusion Image Generation

Segmind has unveiled SegMoE (Segmind Mixture of Diffusion Experts), a new approach that applies the Mixture of Experts (MoE) paradigm to diffusion-based image generation models....

· #multimodal-vlm-architecture #open-source-tooling

Research almost 3 years ago

Stability AI Accelerates Stable Diffusion XL Inference with JAX on Google Cloud TPU v5e

Stability AI has optimized Stable Diffusion XL inference using JAX on Google Cloud's TPU v5e hardware, targeting meaningfully faster image generation throughput. The work focuse...

· #post-production-workflows #workstation-benchmarking #fine-tuning-and-adaptation

Research about 3 years ago

Instruction-Tuning Stable Diffusion with InstructPix2Pix

InstructPix2Pix introduces a method for fine-tuning Stable Diffusion so that users can edit images using plain natural language commands — for example, "make the sky look stormy...

· #fine-tuning-and-adaptation #multimodal-vlm-architecture #post-production-workflows

Research over 3 years ago

Zero-Shot Image Segmentation with CLIPSeg

CLIPSeg brings together CLIP's powerful vision-language understanding with image segmentation, enabling pixel-level semantic analysis without requiring task-specific training da...

· #multimodal-vlm-architecture #post-production-workflows #open-source-tooling