# High-Resolution Image Generation

LoRA model based on stable-diffusion-3.5-medium, focused on high-quality image generation

LyCORIS adapter based on Stable Diffusion XL 1.0, focused on image generation tasks

A LoRA model fine-tuned on FLUX.1-dev for generating Ghibli-style images

Harmon is an innovative unified multimodal understanding and generation framework that coordinates visual representations for understanding and generation through a shared MAR encoder, demonstrating excellent performance in text-to-image generation and multimodal understanding tasks.

A LoRA model fine-tuned based on the FLUX.1-dev base model, specifically designed for generating abstract-style paintings

Janus-Pro is an innovative autoregressive framework that unifies multimodal understanding and generation capabilities.

LyCORIS adapter based on stabilityai/stable-diffusion-3.5-medium, specializing in photorealistic image generation

Lumina-Image 2.0 is a flow-based diffusion transformer model with 2 billion parameters, specializing in text-to-image generation tasks.

LoRA model based on FLUX.1 development version, specializing in text-to-image conversion for teen fashion clothing

Stable Diffusion 3.5 Large is a text-to-image model quantized in GGUF format, suitable for image generation tasks.

FLUX.1-schnell is a text-to-image generation model based on the FLUX architecture, designed for quickly generating high-quality images.

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

Stable Diffusion 1.5 is a high-resolution image generation model based on latent diffusion models, capable of generating high-quality images from text descriptions.

A high-resolution image generation model based on latent diffusion models, capable of producing high-quality artistic images from text descriptions.

A high-resolution image generation model based on latent diffusion models, supporting text-to-image and image-to-image translation.

T2I Adapter is a network that provides additional conditional control for stable diffusion models. This checkpoint offers depth condition control for the StableDiffusionXL model.

Dream Blend is a text-to-image diffusion model capable of generating high-quality images based on text descriptions.

DeepFloyd-IF is a pixel-based three-stage cascaded diffusion model that achieves unprecedented levels of photorealism and language understanding. Its efficiency surpasses current state-of-the-art models, achieving a zero-shot FID-30K score of 6.66 on the COCO dataset.

Colorful-v4.5-Plus is a text-to-image model merged from Anything-v4.5, AbyssOrangeMix3, and ProtogenInfinity, optimized for color performance, environments, fingers, facial expressions, and clothing details.

A text-to-image generation model based on Stable Diffusion, supporting English input to generate high-quality images.

A high-quality artistic fine-tuned model based on SD 1.5, specializing in generating artistic images

The first open-source Chinese-English bilingual Stable Diffusion model, trained on 20 million filtered Chinese image-text pairs