Hugging Face's logo

borischu
/
SVDGolf-downswing

Diffusers
Safetensors
StableVideoDiffusionPipeline
Model card Files Community
borischu commited on
Commit
22a8e50
•
1 Parent(s): 71c8f27

Increase training set resolution, use xt-1-1, linear learning rate

Browse files
Files changed (5) hide show
  1. image_encoder/config.json +2 -2
  2. model_index.json +1 -1
  3. unet/config.json +1 -1
  4. unet/diffusion_pytorch_model.safetensors +1 -1
  5. vae/config.json +1 -1
image_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
3
  "architectures": [
4
  "CLIPVisionModelWithProjection"
5
  ],
@@ -19,5 +19,5 @@
19
  "patch_size": 14,
20
  "projection_dim": 1024,
21
  "torch_dtype": "float16",
22
- "transformers_version": "4.39.1"
23
  }
 
1
  {
2
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt-1-1",
3
  "architectures": [
4
  "CLIPVisionModelWithProjection"
5
  ],
 
19
  "patch_size": 14,
20
  "projection_dim": 1024,
21
  "torch_dtype": "float16",
22
+ "transformers_version": "4.39.2"
23
  }
model_index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "StableVideoDiffusionPipeline",
3
  "_diffusers_version": "0.27.2",
4
- "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
5
  "feature_extractor": [
6
  "transformers",
7
  "CLIPImageProcessor"
 
1
  {
2
  "_class_name": "StableVideoDiffusionPipeline",
3
  "_diffusers_version": "0.27.2",
4
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt-1-1",
5
  "feature_extractor": [
6
  "transformers",
7
  "CLIPImageProcessor"
unet/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "UNetSpatioTemporalConditionModel",
3
  "_diffusers_version": "0.27.2",
4
- "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
5
  "addition_time_embed_dim": 256,
6
  "block_out_channels": [
7
  320,
 
1
  {
2
  "_class_name": "UNetSpatioTemporalConditionModel",
3
  "_diffusers_version": "0.27.2",
4
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt-1-1",
5
  "addition_time_embed_dim": 256,
6
  "block_out_channels": [
7
  320,
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38ec7e8457ee7769a80ed49123ec4655bc695007f5d53fb4b6caab9dc391581a
3
  size 6098682464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a87ea1431da38eaf77ade8b240b98850cd51dd904cac6efe43a81609bc409df
3
  size 6098682464
vae/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "AutoencoderKLTemporalDecoder",
3
  "_diffusers_version": "0.27.2",
4
- "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
5
  "block_out_channels": [
6
  128,
7
  256,
 
1
  {
2
  "_class_name": "AutoencoderKLTemporalDecoder",
3
  "_diffusers_version": "0.27.2",
4
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt-1-1",
5
  "block_out_channels": [
6
  128,
7
  256,