{
  "RunwayML SD 1.5": {
    "path": "runwayml/stable-diffusion-v1-5"
  },
  "StabilityAI SD 2.1": {
    "path": "stabilityai/stable-diffusion-2-1-base"
  },
  "StabilityAI SD-XL 1.0 Base": {
    "path": "stabilityai/stable-diffusion-xl-base-1.0"
  },
  "Segmind SSD-1B": {
    "path": "segmind/SSD-1B"
  },
  "Segmind Tiny": {
    "path": "segmind/tiny-sd"
  },
  "LCM Dreamshaper 7": {
    "path": "SimianLuo/LCM_Dreamshaper_v7"
  },
  "Pixart-α XL 2 Medium": {
    "path": "PixArt-alpha/PixArt-XL-2-512x512"
  },
  "Pixart-α XL 2 Large": {
    "path": "PixArt-alpha/PixArt-XL-2-1024-MS"
  },
  "Warp Wuerstchen": {
    "path": "warp-ai/wuerstchen"
  },
  "Kandinsky 2.1": {
    "path": "kandinsky-community/kandinsky-2-1"
  },
  "Kandinsky 2.2": {
    "path": "kandinsky-community/kandinsky-2-2-decoder"
  },
  "DeepFloyd IF Medium": {
    "path": "DeepFloyd/IF-I-M-v1.0"
  },
  "Tsinghua UniDiffuser": {
    "path": "thu-ml/unidiffuser-v1",
    "desc": "UniDiffuser is a unified diffusion framework to fit all distributions relevant to a set of multi-modal data in one transformer. UniDiffuser is able to perform image, text, text-to-image, image-to-text, and image-text pair generation by setting proper timesteps without additional overhead.\nSpecifically, UniDiffuser employs a variation of transformer, called U-ViT, which parameterizes the joint noise prediction network. Other components perform as encoders and decoders of different modalities, including a pretrained image autoencoder from Stable Diffusion, a pretrained image ViT-B/32 CLIP encoder, a pretrained text ViT-L CLIP encoder, and a GPT-2 text decoder finetuned by ourselves.",
    "preview": "unidiffuser-v1.jpg"
  }
}