# Multimodal Control

SpatialVLA is a vision-language-action model fine-tuned on the fractal dataset, primarily used for robot control tasks.

OpenVLA-OFT is an optimized vision-language-action model that significantly improves speed and success rate through fine-tuning techniques.

Blur control network based on the Stable Diffusion 3.5 large model, used for generating content controlled by blurry images

HiCo is a hierarchical controllable diffusion model specifically designed for layout-to-image generation tasks.

CSGO is a PyTorch implementation for text-to-image generation, supporting image-driven style transfer, text-driven stylized synthesis, and text-editing-driven stylized synthesis.