Upload 6 files

README.md

@@ -1,12 +1,7 @@
 ---
-title: ModelScope Text To Video Synthesis
-emoji: 🚀
-colorFrom: pink
-colorTo: pink
-sdk: gradio
-sdk_version: 3.23.0
-app_file: app.py
-pinned: false
+license: cc-by-nc-4.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis, but with fp16 (half precision) weights
+
+Read all the info here https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis/blob/main/README.md

VQGAN_autoencoder.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:930e9865584beae2405d29bc06a05db3bb6a5b34eedd40a7db29b9156ed7d098
+size 2607657443

configuration.json

@@ -0,0 +1,35 @@
+{   "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"
+    }
+}
+

gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c32c62eebf1112b0693ff9e3ecfa0573ba02cd279420ea4da4af1cbfb39e3b
+size 1972451989

text2video_pytorch_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbba5db98d5432378f9ccdb6bd572768c7ff190dd83b9b76c3218594c793fedd
+size 2823000429