# Art creation assistance

The Dominator is a cutting-edge text-to-image generation model developed by KandooAI, based on Stable Diffusion v1.5, capable of producing high-quality, detail-rich images from textual descriptions.

ControlNet Canny model based on Stable Diffusion 3.5 Medium for controlled image generation via Canny edge detection maps

LoRA fine-tuned model based on FLUX.1-dev, specializing in generating sketch-style portrait artworks

A LoRA diffusion model fine-tuned based on the FLUX.1-dev foundation model for text-to-image generation tasks, supporting specific artistic style conversion

Experimental Japanese Ukiyo-e style image generation model for educational purposes

An anime-style text-to-image generation model based on Stable Diffusion XL, specializing in producing high-quality anime-style images.

PixArt-Σ is a latent diffusion model based on the Transformer architecture, capable of generating high-resolution images (up to 4K) directly from text prompts.

A LoRA model based on Stable Diffusion XL, specifically designed for generating pen sketch-style images.

This repository contains all LoRA models released for Stable Diffusion 1.5 and Pony Diffusion v6 XL, providing various artistic style transformation capabilities.

This is a text-to-image model based on the Stable Diffusion architecture, capable of generating high-quality images according to text descriptions.

T2I Adapter is a network that provides additional conditional control for stable diffusion models. This checkpoint is specifically designed to offer sketch-based conditional control for StableDiffusionXL models.

This is a LoRA model based on Stable Diffusion XL, specifically designed for generating horror-style images.

This is a LoRA model based on Stable Diffusion XL, specifically designed for generating images related to 'offended' expressions and scenes.

Stable Video Diffusion (SVD) is a diffusion model capable of generating short video clips conditioned on static images.

SD-Turbo is a high-speed text-to-image model capable of generating realistic images from text prompts with just a single network inference. Released as a research prototype, it aims to explore compact distilled text-to-image models.

Fine - tuned based on the BLIP model, used to reverse - derive the possible prompt text used to generate an image from the image generated by DALL·E 3

T2I Adapter is a network that provides additional conditional control for stable diffusion models. This checkpoint provides line art conditional control functionality for StableDiffusionXL models.

An adapter model providing Canny edge detection condition control for Stable Diffusion XL, jointly developed by Tencent ARC and Hugging Face

A latent text-to-image diffusion model based on Stable Diffusion XL, capable of image inpainting via masks

ControlNet v1.1 is a Canny edge control model based on Stable Diffusion, enabling image generation by adding edge conditions.

T2I Adapter is a network architecture that provides additional conditional control for Stable Diffusion models. This checkpoint is specifically designed to offer sketch-based conditional control for Stable Diffusion v1.5.

Text-to-image technology based on latent diffusion model, capable of generating realistic images from text input

A control network trained on Stable Diffusion v1.5, specifically designed for fine control of lighting conditions

DreamShaper is a text-to-image generation tool based on the Stable Diffusion model, specializing in artistic creation, particularly excelling in generating anime-style images.

The first multi-style Stable Diffusion model trained from scratch, supporting flexible mixing and individual invocation of three artistic styles

Korean text-to-image generation model based on stable-diffusion-v1-5, with replaced Korean text encoder and tokenizer