# Art Creation Assistance

A latent text-to-image diffusion model optimized for Chinese, capable of generating images from any Chinese prompt

An image editing fine-tuned control LoRA based on THUDM/CogView4-6B model, supporting style transfer and content editing through text instructions

LeX-Enhancer is a lightweight prompt enhancement model distilled from DeepSeek-R1, designed to generate high-quality, visually rich prompt outputs suitable for text-to-image generation.

A LoRA-based text-to-image generation model specializing in brush painting style cartoon images.

A depth control adapter based on the T2I-Adapter architecture, designed to enhance the depth perception capability of SDXL models in image generation

A LoRA model trained on personal illustration styles, suitable for text-to-image generation tasks in the Stable Diffusion framework

Developed jointly by InstantX team and Shakker Labs, the FLUX.1-dev depth control network is designed for text-to-image generation tasks

An image-to-image transformation model based on Stable Diffusion SD1.5, focusing on light consistency control

This is a LoRA adapter weight model based on Stable Diffusion XL, specifically designed for generating images of a particular style.

A specialized inpainting model designed for the CBMX (Cartoon Breast Mix) checkpoint, suitable for image-to-image tasks.

This is a LoRA model based on Stable Diffusion XL, specializing in generating fantasy-style art images.

A diffusion model that generates short video clips from static images, supporting 25-frame video generation at 576x1024 resolution

An unconditional anime face generation model based on diffusion models, capable of generating anime-style face images from random noise

Pixart-α is an efficient text-to-image generation model based on Transformer architecture, capable of generating high-quality 1024-pixel images at extremely low training costs

ControlNet v1.1 is a neural network architecture based on line art image conditions, designed to control pre-trained diffusion models to support additional input conditions.

A ControlNet model specifically designed for image inpainting and expansion, compatible with the Stable Diffusion XL framework

Zero123++ is a diffusion model-based image-to-image generation model capable of generating multi-view 3D objects from a single input image.

Control network model trained on Stable Diffusion XL for precise image generation control via Canny edge detection

ControlNet v1.1 is an enhanced diffusion model structure based on Stable Diffusion, achieving precise image generation control through openpose pose conditions.

A diffusion-based text-to-image generation model supporting image modification and generation, suitable for artistic creation and research purposes

A text-to-image generation system based on latent diffusion model, capable of generating realistic images from text inputs

ControlNet v1.1 is a diffusion model control network based on line art image conditions, designed to enhance the generative control capabilities of models like Stable Diffusion.

ControlNet v1.1 is the successor model to ControlNet v1.0, enabling additional conditional control over diffusion models and supporting image generation based on surface normal estimation.

A ControlNet model trained on HED boundary conditions for controlling edge features in Stable Diffusion-generated images

Art style classification model based on ViT architecture, capable of identifying the art style category of input images

An RLHF fine-tuned Stable Diffusion 2.0 prompt generation model that can automatically expand or generate high-quality image descriptions

A Stable Diffusion-based model capable of transforming photos and artworks into painting styles.

Safe Stable Diffusion is a latent text-to-image diffusion model that generates realistic images from text inputs while actively suppressing inappropriate content generation.

A lightweight GAN model for generating butterfly images, featuring short training time and maintaining performance with few samples