Show-Harness is an embodied interface that enables vision-language models to control robots through discrete semantic actions, allowing both closed-source frontier VLMs and fine-tuned open-source models to perform zero-shot and low-cost robot control. The system includes GUMI, a GUI manipulation interface for demonstration collection, and demonstrates robust generalization across tasks, embodiments, and environments without requiring additional model capacity or embodiment-specific pretraining.
Workflow1111 rebuilds AUTOMATIC1111's stable-diffusion-webui as a single Gradio workflow canvas using seventy-three nodes across eleven media pipelines. It supports text-to-image, image-to-image, upscaling, prompt generation, image interrogation, mask generation, and other AI media tasks, accessible via Hugging Face authentication.