LaCon

30 downloads 2 likes on ModelScope updated

Model card

LaCon: Late-Constraint Diffusion for Steerable Guided Image Synthesis

Chang Liu, Rui Li, Kaidong Zhang, Xin Luo, Dong Liu

[Paper] / [Project] / [GitHub] / [Huggingface] / [Demo]

Official pre-trained model weights of the paper titled "LaCon: Late-Constraint Diffusion for Steerable Guided Image Synthesis".

Model Weights Structure

LaCon/
└── data-preprocessing
    ├── bdcn.pth                      <----- Model weights of BDCN edge detector (Place in `data-preprocessing/bdcn-edge-detection/checkpoints`)
    ├── vgg16.pth                     <----- Preresquisites of BDCN edge detector (Place in `data-preprocessing/bdcn-edge-detection/checkpoints`)
    └── u2net.pth                     <----- Model weights of U2-Net saliency detector (Place in `data-preprocessing/u2net-saliency-detection/checkpoints`)
└── sd-checkpoints
    ├── sd-v1-4.ckpt                  <----- SD v1.4
    ├── kl-f8.ckpt                    <----- VAE model of SD v1.4
    ├── sd-celebahq.ckpt              <----- SD CelebA-HQ
    └── vq-f4.ckpt                    <----- VAE model of SD CelebA-HQ
├── sdv14_edge.pth                    <----- Condition aligner based on SD v1.4, for edge conditions
├── sdv14_color.pth                   <----- Condition aligner based on SD v1.4, for color conditions
├── sdv14_mask.pth                    <----- Condition aligner based on SD v1.4, for mask conditions
├── sd_celeb_edge.pth                 <----- Condition aligner based on SD CelebA-HQ, for edge conditions
└── sd_celeb_stroke.pth               <----- Condition aligner based on SD CelebA-HQ, for color conditions