# Artistic creation assistance

InstructCLIP is an instruction-guided image editing model improved through contrastive learning-based automatic data optimization. It combines CLIP and Stable Diffusion technologies to edit images based on textual instructions.

Edge detection model based on ControlNet architecture for image generation control with Stable Diffusion (SD1.5)

Anteros XXXL is a text-to-image model based on Stable Diffusion XL technology, capable of generating realistic images with a photorealistic texture.

GLIGEN is a diffusion-based grounded text-to-image generation model capable of generating realistic images from text prompts, bounding boxes, and reference images.

RealisticVision_V2 is a text-to-image generation model based on stable diffusion technology, capable of generating high-quality, realistic images from text prompts.

Image generation and editing model based on depth information, supporting high-quality image generation through text prompts and depth maps

ControlNet v1.1 is the successor to ControlNet v1.0, enabling control over diffusion models through additional conditions, particularly suited for doodle-based generation tasks.

ControlNet v1.1 is an extension model based on Stable Diffusion, achieving precise image generation control through Canny edge detection.

High-quality photorealistic image generation model fine-tuned from Stable Diffusion 1.5