# Fast Image Generation

A ControlNet PEFT LoRA model based on HiDream-I1-Full, supporting text-to-image and image-to-image conversion

HiDream-I1-Fast is a GGUF-quantized text-to-image generation model designed for fast image generation tasks.

Hierarchical Distillation (SwD) is a novel framework that accelerates diffusion models (DMs) by progressively increasing spatial resolution during the generation process.

INT4 quantized version of FLUX.1-Canny-dev, capable of generating images based on text descriptions while adhering to the Canny edges of the input image.

A LoRA model based on FLUX.1-dev, specializing in text-to-image tasks, particularly suited for generating mandala-style drawings.

Stable Diffusion 3.5 Medium is a mid-scale text-to-image diffusion model developed by Stability AI, supporting high-quality image generation.

Flux.1 Lite is an 8B-parameter Transformer model distilled from the FLUX.1-dev model, maintaining the same precision (bfloat16) while reducing memory usage by 7GB and improving runtime speed by 23%.

SDXL-Lightning is a progressive adversarial diffusion distillation model based on Stable Diffusion XL (SDXL), focusing on rapid generation of high-quality images.

FLUX.1-schnell is a quantized model based on the GGUF format, specializing in text-to-image and image generation tasks.

KOALA-Lightning-700M is an efficient text-to-image model trained through knowledge distillation based on SDXL-Lightning, significantly improving inference speed while maintaining generation quality

SDXL Flash Edition is a fast text-to-image generation model jointly developed by the Fluently project, achieving rapid generation while maintaining relatively high quality.

Includes a collection of LoRA models designed for optimal performance, adjusted to rank 1 using SVD

A TCD LoRA model based on Stable Diffusion v1.5, optimized for image generation efficiency through Trajectory Consistency Distillation technology.

A text-to-image generation model fine-tuned based on Stable Diffusion v1.5, excelling in artistic and anime-style creations

The Latent Consistency Model is a text-to-image generation model distilled from a fine-tuned version of Stable-Diffusion v1-5's Dreamshaper v7, capable of producing high-quality images in extremely short inference times.

This is an unconditional image generation model based on diffusion models, specifically designed to generate adorable butterfly images.

This is a text-to-image generation model based on stable diffusion technology, capable of producing high-quality images from text descriptions.

This is a text-to-image generation model based on Stable Diffusion technology, trained using the Dreambooth method, focusing on generating images with specific styles.