add modelscope

html/reference.json

@@ -88,5 +88,10 @@
     "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": "thu-ml--unidiffuser-v1.jpg"
+  },
+  "ModelScope T2V": {
+    "path": "damo-vilab/text-to-video-ms-1.7b",
+    "desc": "The text-to-video generation diffusion model consists of three sub-networks: text feature extraction model, text feature-to-video latent space diffusion model, and video latent space to video visual space model. The overall model parameters are about 1.7 billion. Currently, it only supports English input. The diffusion model adopts a UNet3D structure, and implements video generation through the iterative denoising process from the pure Gaussian noise video.",
+    "preview": "damo-vilab--text-to-video-ms-1.7b.jpg"
   }
 }