Upload TextToVideoSDPipeline

model_index.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "TextToVideoSDPipeline",
   "_diffusers_version": "0.25.0.dev0",
-  "_name_or_path": "damo-vilab/text-to-video-ms-1.7b",
+  "_name_or_path": "diffusers/i2vgen-xl-diffusers",
   "scheduler": [
     "diffusers",
     "DDIMScheduler"

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "i2vgen-xl-text-encoder",
+  "_name_or_path": "/home/sayak/.cache/huggingface/hub/models--diffusers--i2vgen-xl-diffusers/snapshots/6f9dab376562e81e38abe6dc58d7b84c20fedd62/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],

tokenizer/special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "!",
+  "pad_token": {
+    "content": "!",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

unet/config.json

@@ -25,7 +25,7 @@
   "norm_num_groups": 32,
   "num_attention_heads": null,
   "out_channels": 4,
-  "sample_size": null,
+  "sample_size": 32,
   "up_block_types": [
     "UpBlock3D",
     "CrossAttnUpBlock3D",

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.25.0.dev0",
-  "_name_or_path": "i2vgen-xl-vae",
+  "_name_or_path": "/home/sayak/.cache/huggingface/hub/models--diffusers--i2vgen-xl-diffusers/snapshots/6f9dab376562e81e38abe6dc58d7b84c20fedd62/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,