This is an experimental Stable Diffusion 1.5 distillation model that uses the v-prediction flow matching method and geometric guided adaptive block weighting technology. It is currently in the research phase, the training is ongoing, and the results have not been verified.

Computer VisionDiffusers

This is a LoRA-adapted weight model based on stabilityai/stable-diffusion-xl-base-1.0, obtained through DreamBooth training, focusing on generating images of specific characters.

Computer VisionDiffusers

Lotus is a vision foundation model based on diffusion models, focusing on high-quality dense prediction tasks, particularly depth estimation. Compared to the previous version, this model adopts disparity space (inverse depth) training, achieving superior performance and more stable video depth estimation.

Computer VisionDiffusers

This is a LoRA model based on Stable Diffusion XL 1.0, focusing on generating photorealistic images, currently still in the training phase.

Computer VisionDiffusers

This is a LoRA model based on Stable Diffusion XL 1.0, specializing in generating interior architecture and design scene images. The current version is still in the training phase and may exhibit suboptimal performance in certain scenarios.

Computer VisionDiffusers

SimPO is a simple and effective preference optimization method that simplifies the alignment process by eliminating the need for a reference model. This method uses the average log probability as an implicit reward and achieves stable training through a length-normalized objective, outperforming existing methods such as DPO in multiple benchmarks.

Natural Language ProcessingTransformers

This is an unofficial InstantID implementation for StableDiffusion 1.5, supporting both training and inference, and can be combined with various fine-tuned models.

Computer VisionDiffusers

Emi is an AI dedicated to AI art image generation, developed using Stable Diffusion XL 1.0 technology, without training on unauthorized images

Computer VisionDiffusers

BK-SDM is a stable diffusion model with architecture compression. By removing the residual and attention blocks in the U-Net and conducting knowledge distillation training on limited data, it achieves efficient text-to-image synthesis. This model significantly reduces the number of parameters while maintaining good generation quality.

MultimodalDiffusers

A virtual try-on system built on the Stable Diffusion framework, integrating DreamBooth training, EfficientNetB3 feature extraction, and OpenPose pose detection technologies

Computer VisionDiffusers

The Openjourney fine-tuned model is trained based on Stable Diffusion 1.5, using over 60,000 images for training to optimize image generation quality.

Computer VisionDiffusers

A 512px resolution color style model based on Stable Diffusion 1.5, activated by the prompt 'colorjizz' to generate vibrant color effects through 130 training images

Computer VisionDiffusers

This is a pixel art image generation model based on Stable Diffusion, crafted with 184 training images and 8,000 training steps, specifically optimized for facial detail representation.

Computer VisionDiffusers

A Stable Diffusion-based voxel style image generation model, containing 143 training images and 8000 training steps, supporting the generation of voxel-style images through specific prompts.

Computer VisionDiffusers

Stable Diffusion is a latent diffusion model capable of generating realistic images from text inputs. Version 1.3 includes aesthetic optimization training based on v1.2.

MultimodalPytorch