Add files

README.md

@@ -1,3 +1,6 @@
 ---
 license: apache-2.0
 ---
+
+The original repo is [here](https://modelscope.cn/models/damo/text-to-video-synthesis/summary).
+

VQGAN_autoencoder.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ecb782561455673c4b78d05093494b9c539fc6bfc08f3a9a4a0dd7b0b10f36
+size 5214865159

configuration.json

@@ -0,0 +1,34 @@
+{   "framework": "pytorch",
+    "task": "text-to-video-synthesis",
+    "model": {
+        "type": "latent-text-to-video-synthesis",
+        "model_args": {
+            "ckpt_clip": "open_clip_pytorch_model.bin",
+            "ckpt_unet": "text2video_pytorch_model.pth",
+            "ckpt_autoencoder": "VQGAN_autoencoder.pth",
+            "max_frames": 16,
+            "tiny_gpu": 1
+        },
+        "model_cfg": {
+            "unet_in_dim": 4,
+            "unet_dim": 320,
+            "unet_y_dim": 768,
+            "unet_context_dim": 1024,
+            "unet_out_dim": 4,
+            "unet_dim_mult": [1, 2, 4, 4],
+            "unet_num_heads": 8,
+            "unet_head_dim": 64,
+            "unet_res_blocks": 2,
+            "unet_attn_scales": [1, 0.5, 0.25],
+            "unet_dropout": 0.1,
+            "temporal_attention": "True",
+            "num_timesteps": 1000,
+            "mean_type": "eps",
+            "var_type": "fixed_small",
+            "loss_type": "mse"
+        }
+    },
+    "pipeline": {
+        "type": "latent-text-to-video-synthesis"
+    }
+}

open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a78ef8e8c73fd0df621682e7a8e8eb36c6916cb3c16b291a082ecd52ab79cc4
+size 3944692325

text2video_pytorch_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9609d02717b799137a97244844ab6df0d1a071568a1d24dcb62d9050f3a24a3
+size 5645549049