# High quality with low steps

A text-to-image model based on SDXL, specializing in high-fidelity image generation with optimized facial textures and scene coordination

A series of photorealistic image generation models developed based on the FLUX framework, including multiple fine-tuned versions and LoRA adapters

OpenFLUX.1 is a fine-tuned version based on the FLUX.1-schnell model, with distillation removed to allow user fine-tuning. It is a text-to-image generation model capable of producing high-quality images in 1-4 steps.

DMD2 is a fast image synthesis technology based on diffusion models, achieving efficient image generation through an improved distribution matching distillation method.

SLAM-LoRA is a lightweight model based on Stable Diffusion XL, reducing inference steps to just 2-4 through subpath linear approximation technology.

Fluently V4.0-LCM is an all-purpose task model that achieves high-speed image generation by integrating multiple models and LCM technology, featuring precise anatomical structures and high artistic expression.

Text-to-image generation model based on stable diffusion technology, converted to ONNX format and tested with OnnxStack