Hugging Face's logo

ali-vilab
/
i2vgen-xl

Text-to-Video
Diffusers
Safetensors
I2VGenXLPipeline
image-to-video
Model card Files Community
15

Update with fp16 variants

#8
by sayakpaul HF staff - opened
base: refs/heads/main
←
from: refs/pr/8
Discussion Files changed
+25
-13
Files changed (10) hide show
  1. image_encoder/config.json +3 -3
  2. image_encoder/model.fp16.safetensors +3 -0
  3. model_index.json +2 -2
  4. scheduler/scheduler_config.json +1 -1
  5. text_encoder/config.json +3 -3
  6. text_encoder/model.fp16.safetensors +3 -0
  7. unet/config.json +2 -2
  8. unet/diffusion_pytorch_model.fp16.safetensors +3 -0
  9. vae/config.json +2 -2
  10. vae/diffusion_pytorch_model.fp16.safetensors +3 -0
image_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/home/patrick/.cache/huggingface/hub/models--diffusers--i2vgen-xl/snapshots/f2430483897b1745040925549ab549dcfbd9ce86/image_encoder",
3
  "architectures": [
4
  "CLIPVisionModelWithProjection"
5
  ],
@@ -18,6 +18,6 @@
18
  "num_hidden_layers": 32,
19
  "patch_size": 14,
20
  "projection_dim": 1024,
21
- "torch_dtype": "float32",
22
- "transformers_version": "4.38.0.dev0"
23
  }
 
1
  {
2
+ "_name_or_path": "i2vgen-xl/image_encoder",
3
  "architectures": [
4
  "CLIPVisionModelWithProjection"
5
  ],
 
18
  "num_hidden_layers": 32,
19
  "patch_size": 14,
20
  "projection_dim": 1024,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.36.2"
23
  }
image_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae616c24393dd1854372b0639e5541666f7521cbe219669255e865cb7f89466a
3
+ size 1264217240
model_index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "I2VGenXLPipeline",
3
- "_diffusers_version": "0.26.0.dev0",
4
- "_name_or_path": "diffusers/i2vgen-xl",
5
  "feature_extractor": [
6
  "transformers",
7
  "CLIPImageProcessor"
 
1
  {
2
  "_class_name": "I2VGenXLPipeline",
3
+ "_diffusers_version": "0.26.1",
4
+ "_name_or_path": "i2vgen-xl",
5
  "feature_extractor": [
6
  "transformers",
7
  "CLIPImageProcessor"
scheduler/scheduler_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "DDIMScheduler",
3
- "_diffusers_version": "0.26.0.dev0",
4
  "beta_end": 0.02,
5
  "beta_schedule": "squaredcos_cap_v2",
6
  "beta_start": 0.0001,
 
1
  {
2
  "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.26.1",
4
  "beta_end": 0.02,
5
  "beta_schedule": "squaredcos_cap_v2",
6
  "beta_start": 0.0001,
text_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/home/patrick/.cache/huggingface/hub/models--diffusers--i2vgen-xl/snapshots/f2430483897b1745040925549ab549dcfbd9ce86/text_encoder",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -19,7 +19,7 @@
19
  "num_hidden_layers": 24,
20
  "pad_token_id": 1,
21
  "projection_dim": 1024,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.38.0.dev0",
24
  "vocab_size": 49408
25
  }
 
1
  {
2
+ "_name_or_path": "i2vgen-xl/text_encoder",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
19
  "num_hidden_layers": 24,
20
  "pad_token_id": 1,
21
  "projection_dim": 1024,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.36.2",
24
  "vocab_size": 49408
25
  }
text_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb4cf70d7768f4f61bb25e98b2ddaf545f6b33ecc2d7cc3eaa4670a09722fd2
3
+ size 706014768
unet/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "I2VGenXLUNet",
3
- "_diffusers_version": "0.26.0.dev0",
4
- "_name_or_path": "/home/patrick/.cache/huggingface/hub/models--diffusers--i2vgen-xl/snapshots/f2430483897b1745040925549ab549dcfbd9ce86/unet",
5
  "block_out_channels": [
6
  320,
7
  640,
 
1
  {
2
  "_class_name": "I2VGenXLUNet",
3
+ "_diffusers_version": "0.26.1",
4
+ "_name_or_path": "i2vgen-xl/unet",
5
  "block_out_channels": [
6
  320,
7
  640,
unet/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ef043141380ab4f5f0698d0b735e4020d6049819e3c756ddbe2672a48a466d4
3
+ size 2841124432
vae/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.26.0.dev0",
4
- "_name_or_path": "/home/patrick/.cache/huggingface/hub/models--diffusers--i2vgen-xl/snapshots/f2430483897b1745040925549ab549dcfbd9ce86/vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.26.1",
4
+ "_name_or_path": "i2vgen-xl/vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
vae/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
3
+ size 167335342