AlonzoLeeeooo commited on
Commit
4006f6c
1 Parent(s): ae04526

Upload 18 files

Browse files
i2vgenxl/feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
i2vgenxl/gitattributes ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ doc/introduction.pdf filter=lfs diff=lfs merge=lfs -text
37
+ source/i2vgen_fig_04.png filter=lfs diff=lfs merge=lfs -text
i2vgenxl/image_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "i2vgen-xl/image_encoder",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 1280,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 32,
19
+ "patch_size": 14,
20
+ "projection_dim": 1024,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.36.2"
23
+ }
i2vgenxl/image_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed1e5af7b4042ca30ec29999a4a5cfcac90b7fb610fd05ace834f2dcbb763eab
3
+ size 2528371296
i2vgenxl/model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "I2VGenXLPipeline",
3
+ "_diffusers_version": "0.26.1",
4
+ "_name_or_path": "i2vgen-xl",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ "transformers",
11
+ "CLIPVisionModelWithProjection"
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "DDIMScheduler"
16
+ ],
17
+ "text_encoder": [
18
+ "transformers",
19
+ "CLIPTextModel"
20
+ ],
21
+ "tokenizer": [
22
+ "transformers",
23
+ "CLIPTokenizer"
24
+ ],
25
+ "unet": [
26
+ "diffusers",
27
+ "I2VGenXLUNet"
28
+ ],
29
+ "vae": [
30
+ "diffusers",
31
+ "AutoencoderKL"
32
+ ]
33
+ }
i2vgenxl/models/models_stable_diffusion_image_key_temporal_attention_x1.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["input_blocks.0.0.weight", "input_blocks.0.0.bias", "input_blocks.1.0.in_layers.0.weight", "input_blocks.1.0.in_layers.0.bias", "input_blocks.1.0.in_layers.2.weight", "input_blocks.1.0.in_layers.2.bias", "input_blocks.1.0.emb_layers.1.weight", "input_blocks.1.0.emb_layers.1.bias", "input_blocks.1.0.out_layers.0.weight", "input_blocks.1.0.out_layers.0.bias", "input_blocks.1.0.out_layers.3.weight", "input_blocks.1.0.out_layers.3.bias", "input_blocks.1.1.norm.weight", "input_blocks.1.1.norm.bias", "input_blocks.1.1.proj_in.weight", "input_blocks.1.1.proj_in.bias", "input_blocks.1.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.1.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.1.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.1.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.1.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.1.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.1.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.1.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.1.1.transformer_blocks.0.norm1.weight", "input_blocks.1.1.transformer_blocks.0.norm1.bias", "input_blocks.1.1.transformer_blocks.0.norm2.weight", "input_blocks.1.1.transformer_blocks.0.norm2.bias", "input_blocks.1.1.transformer_blocks.0.norm3.weight", "input_blocks.1.1.transformer_blocks.0.norm3.bias", "input_blocks.1.1.proj_out.weight", "input_blocks.1.1.proj_out.bias", "input_blocks.2.0.in_layers.0.weight", "input_blocks.2.0.in_layers.0.bias", "input_blocks.2.0.in_layers.2.weight", "input_blocks.2.0.in_layers.2.bias", "input_blocks.2.0.emb_layers.1.weight", "input_blocks.2.0.emb_layers.1.bias", "input_blocks.2.0.out_layers.0.weight", "input_blocks.2.0.out_layers.0.bias", "input_blocks.2.0.out_layers.3.weight", "input_blocks.2.0.out_layers.3.bias", "input_blocks.2.1.norm.weight", "input_blocks.2.1.norm.bias", "input_blocks.2.1.proj_in.weight", "input_blocks.2.1.proj_in.bias", "input_blocks.2.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.2.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.2.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.2.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.2.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.2.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.2.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.2.1.transformer_blocks.0.norm1.weight", "input_blocks.2.1.transformer_blocks.0.norm1.bias", "input_blocks.2.1.transformer_blocks.0.norm2.weight", "input_blocks.2.1.transformer_blocks.0.norm2.bias", "input_blocks.2.1.transformer_blocks.0.norm3.weight", "input_blocks.2.1.transformer_blocks.0.norm3.bias", "input_blocks.2.1.proj_out.weight", "input_blocks.2.1.proj_out.bias", "input_blocks.3.op.weight", "input_blocks.3.op.bias", "input_blocks.4.0.in_layers.0.weight", "input_blocks.4.0.in_layers.0.bias", "input_blocks.4.0.in_layers.2.weight", "input_blocks.4.0.in_layers.2.bias", "input_blocks.4.0.emb_layers.1.weight", "input_blocks.4.0.emb_layers.1.bias", "input_blocks.4.0.out_layers.0.weight", "input_blocks.4.0.out_layers.0.bias", "input_blocks.4.0.out_layers.3.weight", "input_blocks.4.0.out_layers.3.bias", "input_blocks.4.0.skip_connection.weight", "input_blocks.4.0.skip_connection.bias", "input_blocks.4.1.norm.weight", "input_blocks.4.1.norm.bias", "input_blocks.4.1.proj_in.weight", "input_blocks.4.1.proj_in.bias", "input_blocks.4.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.4.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.4.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.4.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.4.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.4.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.4.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.4.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.4.1.transformer_blocks.0.norm1.weight", "input_blocks.4.1.transformer_blocks.0.norm1.bias", "input_blocks.4.1.transformer_blocks.0.norm2.weight", "input_blocks.4.1.transformer_blocks.0.norm2.bias", "input_blocks.4.1.transformer_blocks.0.norm3.weight", "input_blocks.4.1.transformer_blocks.0.norm3.bias", "input_blocks.4.1.proj_out.weight", "input_blocks.4.1.proj_out.bias", "input_blocks.5.0.in_layers.0.weight", "input_blocks.5.0.in_layers.0.bias", "input_blocks.5.0.in_layers.2.weight", "input_blocks.5.0.in_layers.2.bias", "input_blocks.5.0.emb_layers.1.weight", "input_blocks.5.0.emb_layers.1.bias", "input_blocks.5.0.out_layers.0.weight", "input_blocks.5.0.out_layers.0.bias", "input_blocks.5.0.out_layers.3.weight", "input_blocks.5.0.out_layers.3.bias", "input_blocks.5.1.norm.weight", "input_blocks.5.1.norm.bias", "input_blocks.5.1.proj_in.weight", "input_blocks.5.1.proj_in.bias", "input_blocks.5.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.5.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.5.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.5.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.5.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.5.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.5.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.5.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.5.1.transformer_blocks.0.norm1.weight", "input_blocks.5.1.transformer_blocks.0.norm1.bias", "input_blocks.5.1.transformer_blocks.0.norm2.weight", "input_blocks.5.1.transformer_blocks.0.norm2.bias", "input_blocks.5.1.transformer_blocks.0.norm3.weight", "input_blocks.5.1.transformer_blocks.0.norm3.bias", "input_blocks.5.1.proj_out.weight", "input_blocks.5.1.proj_out.bias", "input_blocks.6.op.weight", "input_blocks.6.op.bias", "input_blocks.7.0.in_layers.0.weight", "input_blocks.7.0.in_layers.0.bias", "input_blocks.7.0.in_layers.2.weight", "input_blocks.7.0.in_layers.2.bias", "input_blocks.7.0.emb_layers.1.weight", "input_blocks.7.0.emb_layers.1.bias", "input_blocks.7.0.out_layers.0.weight", "input_blocks.7.0.out_layers.0.bias", "input_blocks.7.0.out_layers.3.weight", "input_blocks.7.0.out_layers.3.bias", "input_blocks.7.0.skip_connection.weight", "input_blocks.7.0.skip_connection.bias", "input_blocks.7.1.norm.weight", "input_blocks.7.1.norm.bias", "input_blocks.7.1.proj_in.weight", "input_blocks.7.1.proj_in.bias", "input_blocks.7.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.7.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.7.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.7.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.7.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.7.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.7.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.7.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.7.1.transformer_blocks.0.norm1.weight", "input_blocks.7.1.transformer_blocks.0.norm1.bias", "input_blocks.7.1.transformer_blocks.0.norm2.weight", "input_blocks.7.1.transformer_blocks.0.norm2.bias", "input_blocks.7.1.transformer_blocks.0.norm3.weight", "input_blocks.7.1.transformer_blocks.0.norm3.bias", "input_blocks.7.1.proj_out.weight", "input_blocks.7.1.proj_out.bias", "input_blocks.8.0.in_layers.0.weight", "input_blocks.8.0.in_layers.0.bias", "input_blocks.8.0.in_layers.2.weight", "input_blocks.8.0.in_layers.2.bias", "input_blocks.8.0.emb_layers.1.weight", "input_blocks.8.0.emb_layers.1.bias", "input_blocks.8.0.out_layers.0.weight", "input_blocks.8.0.out_layers.0.bias", "input_blocks.8.0.out_layers.3.weight", "input_blocks.8.0.out_layers.3.bias", "input_blocks.8.1.norm.weight", "input_blocks.8.1.norm.bias", "input_blocks.8.1.proj_in.weight", "input_blocks.8.1.proj_in.bias", "input_blocks.8.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.8.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.8.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.8.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.8.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.8.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.8.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.8.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.8.1.transformer_blocks.0.norm1.weight", "input_blocks.8.1.transformer_blocks.0.norm1.bias", "input_blocks.8.1.transformer_blocks.0.norm2.weight", "input_blocks.8.1.transformer_blocks.0.norm2.bias", "input_blocks.8.1.transformer_blocks.0.norm3.weight", "input_blocks.8.1.transformer_blocks.0.norm3.bias", "input_blocks.8.1.proj_out.weight", "input_blocks.8.1.proj_out.bias", "input_blocks.9.op.weight", "input_blocks.9.op.bias", "input_blocks.10.0.in_layers.0.weight", "input_blocks.10.0.in_layers.0.bias", "input_blocks.10.0.in_layers.2.weight", "input_blocks.10.0.in_layers.2.bias", "input_blocks.10.0.emb_layers.1.weight", "input_blocks.10.0.emb_layers.1.bias", "input_blocks.10.0.out_layers.0.weight", "input_blocks.10.0.out_layers.0.bias", "input_blocks.10.0.out_layers.3.weight", "input_blocks.10.0.out_layers.3.bias", "input_blocks.11.0.in_layers.0.weight", "input_blocks.11.0.in_layers.0.bias", "input_blocks.11.0.in_layers.2.weight", "input_blocks.11.0.in_layers.2.bias", "input_blocks.11.0.emb_layers.1.weight", "input_blocks.11.0.emb_layers.1.bias", "input_blocks.11.0.out_layers.0.weight", "input_blocks.11.0.out_layers.0.bias", "input_blocks.11.0.out_layers.3.weight", "input_blocks.11.0.out_layers.3.bias", "middle_block.0.in_layers.0.weight", "middle_block.0.in_layers.0.bias", "middle_block.0.in_layers.2.weight", "middle_block.0.in_layers.2.bias", "middle_block.0.emb_layers.1.weight", "middle_block.0.emb_layers.1.bias", "middle_block.0.out_layers.0.weight", "middle_block.0.out_layers.0.bias", "middle_block.0.out_layers.3.weight", "middle_block.0.out_layers.3.bias", "middle_block.1.norm.weight", "middle_block.1.norm.bias", "middle_block.1.proj_in.weight", "middle_block.1.proj_in.bias", "middle_block.1.transformer_blocks.0.attn1.to_q.weight", "middle_block.1.transformer_blocks.0.attn1.to_k.weight", "middle_block.1.transformer_blocks.0.attn1.to_v.weight", "middle_block.1.transformer_blocks.0.attn1.to_out.0.weight", "middle_block.1.transformer_blocks.0.attn1.to_out.0.bias", "middle_block.1.transformer_blocks.0.ff.net.0.proj.weight", "middle_block.1.transformer_blocks.0.ff.net.0.proj.bias", "middle_block.1.transformer_blocks.0.ff.net.2.weight", "middle_block.1.transformer_blocks.0.ff.net.2.bias", "middle_block.1.transformer_blocks.0.attn2.to_q.weight", "middle_block.1.transformer_blocks.0.attn2.to_k.weight", "middle_block.1.transformer_blocks.0.attn2.to_v.weight", "middle_block.1.transformer_blocks.0.attn2.to_out.0.weight", "middle_block.1.transformer_blocks.0.attn2.to_out.0.bias", "middle_block.1.transformer_blocks.0.norm1.weight", "middle_block.1.transformer_blocks.0.norm1.bias", "middle_block.1.transformer_blocks.0.norm2.weight", "middle_block.1.transformer_blocks.0.norm2.bias", "middle_block.1.transformer_blocks.0.norm3.weight", "middle_block.1.transformer_blocks.0.norm3.bias", "middle_block.1.proj_out.weight", "middle_block.1.proj_out.bias", "middle_block.3.in_layers.0.weight", "middle_block.3.in_layers.0.bias", "middle_block.3.in_layers.2.weight", "middle_block.3.in_layers.2.bias", "middle_block.3.emb_layers.1.weight", "middle_block.3.emb_layers.1.bias", "middle_block.3.out_layers.0.weight", "middle_block.3.out_layers.0.bias", "middle_block.3.out_layers.3.weight", "middle_block.3.out_layers.3.bias", "output_blocks.0.0.in_layers.0.weight", "output_blocks.0.0.in_layers.0.bias", "output_blocks.0.0.in_layers.2.weight", "output_blocks.0.0.in_layers.2.bias", "output_blocks.0.0.emb_layers.1.weight", "output_blocks.0.0.emb_layers.1.bias", "output_blocks.0.0.out_layers.0.weight", "output_blocks.0.0.out_layers.0.bias", "output_blocks.0.0.out_layers.3.weight", "output_blocks.0.0.out_layers.3.bias", "output_blocks.0.0.skip_connection.weight", "output_blocks.0.0.skip_connection.bias", "output_blocks.1.0.in_layers.0.weight", "output_blocks.1.0.in_layers.0.bias", "output_blocks.1.0.in_layers.2.weight", "output_blocks.1.0.in_layers.2.bias", "output_blocks.1.0.emb_layers.1.weight", "output_blocks.1.0.emb_layers.1.bias", "output_blocks.1.0.out_layers.0.weight", "output_blocks.1.0.out_layers.0.bias", "output_blocks.1.0.out_layers.3.weight", "output_blocks.1.0.out_layers.3.bias", "output_blocks.1.0.skip_connection.weight", "output_blocks.1.0.skip_connection.bias", "output_blocks.2.0.in_layers.0.weight", "output_blocks.2.0.in_layers.0.bias", "output_blocks.2.0.in_layers.2.weight", "output_blocks.2.0.in_layers.2.bias", "output_blocks.2.0.emb_layers.1.weight", "output_blocks.2.0.emb_layers.1.bias", "output_blocks.2.0.out_layers.0.weight", "output_blocks.2.0.out_layers.0.bias", "output_blocks.2.0.out_layers.3.weight", "output_blocks.2.0.out_layers.3.bias", "output_blocks.2.0.skip_connection.weight", "output_blocks.2.0.skip_connection.bias", "output_blocks.2.1.conv.weight", "output_blocks.2.1.conv.bias", "output_blocks.3.0.in_layers.0.weight", "output_blocks.3.0.in_layers.0.bias", "output_blocks.3.0.in_layers.2.weight", "output_blocks.3.0.in_layers.2.bias", "output_blocks.3.0.emb_layers.1.weight", "output_blocks.3.0.emb_layers.1.bias", "output_blocks.3.0.out_layers.0.weight", "output_blocks.3.0.out_layers.0.bias", "output_blocks.3.0.out_layers.3.weight", "output_blocks.3.0.out_layers.3.bias", "output_blocks.3.0.skip_connection.weight", "output_blocks.3.0.skip_connection.bias", "output_blocks.3.1.norm.weight", "output_blocks.3.1.norm.bias", "output_blocks.3.1.proj_in.weight", "output_blocks.3.1.proj_in.bias", "output_blocks.3.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.3.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.3.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.3.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.3.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.3.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.3.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.3.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.3.1.transformer_blocks.0.norm1.weight", "output_blocks.3.1.transformer_blocks.0.norm1.bias", "output_blocks.3.1.transformer_blocks.0.norm2.weight", "output_blocks.3.1.transformer_blocks.0.norm2.bias", "output_blocks.3.1.transformer_blocks.0.norm3.weight", "output_blocks.3.1.transformer_blocks.0.norm3.bias", "output_blocks.3.1.proj_out.weight", "output_blocks.3.1.proj_out.bias", "output_blocks.4.0.in_layers.0.weight", "output_blocks.4.0.in_layers.0.bias", "output_blocks.4.0.in_layers.2.weight", "output_blocks.4.0.in_layers.2.bias", "output_blocks.4.0.emb_layers.1.weight", "output_blocks.4.0.emb_layers.1.bias", "output_blocks.4.0.out_layers.0.weight", "output_blocks.4.0.out_layers.0.bias", "output_blocks.4.0.out_layers.3.weight", "output_blocks.4.0.out_layers.3.bias", "output_blocks.4.0.skip_connection.weight", "output_blocks.4.0.skip_connection.bias", "output_blocks.4.1.norm.weight", "output_blocks.4.1.norm.bias", "output_blocks.4.1.proj_in.weight", "output_blocks.4.1.proj_in.bias", "output_blocks.4.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.4.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.4.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.4.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.4.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.4.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.4.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.4.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.4.1.transformer_blocks.0.norm1.weight", "output_blocks.4.1.transformer_blocks.0.norm1.bias", "output_blocks.4.1.transformer_blocks.0.norm2.weight", "output_blocks.4.1.transformer_blocks.0.norm2.bias", "output_blocks.4.1.transformer_blocks.0.norm3.weight", "output_blocks.4.1.transformer_blocks.0.norm3.bias", "output_blocks.4.1.proj_out.weight", "output_blocks.4.1.proj_out.bias", "output_blocks.5.0.in_layers.0.weight", "output_blocks.5.0.in_layers.0.bias", "output_blocks.5.0.in_layers.2.weight", "output_blocks.5.0.in_layers.2.bias", "output_blocks.5.0.emb_layers.1.weight", "output_blocks.5.0.emb_layers.1.bias", "output_blocks.5.0.out_layers.0.weight", "output_blocks.5.0.out_layers.0.bias", "output_blocks.5.0.out_layers.3.weight", "output_blocks.5.0.out_layers.3.bias", "output_blocks.5.0.skip_connection.weight", "output_blocks.5.0.skip_connection.bias", "output_blocks.5.1.norm.weight", "output_blocks.5.1.norm.bias", "output_blocks.5.1.proj_in.weight", "output_blocks.5.1.proj_in.bias", "output_blocks.5.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.5.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.5.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.5.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.5.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.5.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.5.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.5.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.5.1.transformer_blocks.0.norm1.weight", "output_blocks.5.1.transformer_blocks.0.norm1.bias", "output_blocks.5.1.transformer_blocks.0.norm2.weight", "output_blocks.5.1.transformer_blocks.0.norm2.bias", "output_blocks.5.1.transformer_blocks.0.norm3.weight", "output_blocks.5.1.transformer_blocks.0.norm3.bias", "output_blocks.5.1.proj_out.weight", "output_blocks.5.1.proj_out.bias", "output_blocks.5.3.conv.weight", "output_blocks.5.3.conv.bias", "output_blocks.6.0.in_layers.0.weight", "output_blocks.6.0.in_layers.0.bias", "output_blocks.6.0.in_layers.2.weight", "output_blocks.6.0.in_layers.2.bias", "output_blocks.6.0.emb_layers.1.weight", "output_blocks.6.0.emb_layers.1.bias", "output_blocks.6.0.out_layers.0.weight", "output_blocks.6.0.out_layers.0.bias", "output_blocks.6.0.out_layers.3.weight", "output_blocks.6.0.out_layers.3.bias", "output_blocks.6.0.skip_connection.weight", "output_blocks.6.0.skip_connection.bias", "output_blocks.6.1.norm.weight", "output_blocks.6.1.norm.bias", "output_blocks.6.1.proj_in.weight", "output_blocks.6.1.proj_in.bias", "output_blocks.6.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.6.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.6.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.6.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.6.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.6.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.6.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.6.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.6.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.6.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.6.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.6.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.6.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.6.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.6.1.transformer_blocks.0.norm1.weight", "output_blocks.6.1.transformer_blocks.0.norm1.bias", "output_blocks.6.1.transformer_blocks.0.norm2.weight", "output_blocks.6.1.transformer_blocks.0.norm2.bias", "output_blocks.6.1.transformer_blocks.0.norm3.weight", "output_blocks.6.1.transformer_blocks.0.norm3.bias", "output_blocks.6.1.proj_out.weight", "output_blocks.6.1.proj_out.bias", "output_blocks.7.0.in_layers.0.weight", "output_blocks.7.0.in_layers.0.bias", "output_blocks.7.0.in_layers.2.weight", "output_blocks.7.0.in_layers.2.bias", "output_blocks.7.0.emb_layers.1.weight", "output_blocks.7.0.emb_layers.1.bias", "output_blocks.7.0.out_layers.0.weight", "output_blocks.7.0.out_layers.0.bias", "output_blocks.7.0.out_layers.3.weight", "output_blocks.7.0.out_layers.3.bias", "output_blocks.7.0.skip_connection.weight", "output_blocks.7.0.skip_connection.bias", "output_blocks.7.1.norm.weight", "output_blocks.7.1.norm.bias", "output_blocks.7.1.proj_in.weight", "output_blocks.7.1.proj_in.bias", "output_blocks.7.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.7.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.7.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.7.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.7.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.7.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.7.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.7.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.7.1.transformer_blocks.0.norm1.weight", "output_blocks.7.1.transformer_blocks.0.norm1.bias", "output_blocks.7.1.transformer_blocks.0.norm2.weight", "output_blocks.7.1.transformer_blocks.0.norm2.bias", "output_blocks.7.1.transformer_blocks.0.norm3.weight", "output_blocks.7.1.transformer_blocks.0.norm3.bias", "output_blocks.7.1.proj_out.weight", "output_blocks.7.1.proj_out.bias", "output_blocks.8.0.in_layers.0.weight", "output_blocks.8.0.in_layers.0.bias", "output_blocks.8.0.in_layers.2.weight", "output_blocks.8.0.in_layers.2.bias", "output_blocks.8.0.emb_layers.1.weight", "output_blocks.8.0.emb_layers.1.bias", "output_blocks.8.0.out_layers.0.weight", "output_blocks.8.0.out_layers.0.bias", "output_blocks.8.0.out_layers.3.weight", "output_blocks.8.0.out_layers.3.bias", "output_blocks.8.0.skip_connection.weight", "output_blocks.8.0.skip_connection.bias", "output_blocks.8.1.norm.weight", "output_blocks.8.1.norm.bias", "output_blocks.8.1.proj_in.weight", "output_blocks.8.1.proj_in.bias", "output_blocks.8.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.8.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.8.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.8.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.8.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.8.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.8.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.8.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.8.1.transformer_blocks.0.norm1.weight", "output_blocks.8.1.transformer_blocks.0.norm1.bias", "output_blocks.8.1.transformer_blocks.0.norm2.weight", "output_blocks.8.1.transformer_blocks.0.norm2.bias", "output_blocks.8.1.transformer_blocks.0.norm3.weight", "output_blocks.8.1.transformer_blocks.0.norm3.bias", "output_blocks.8.1.proj_out.weight", "output_blocks.8.1.proj_out.bias", "output_blocks.8.3.conv.weight", "output_blocks.8.3.conv.bias", "output_blocks.9.0.in_layers.0.weight", "output_blocks.9.0.in_layers.0.bias", "output_blocks.9.0.in_layers.2.weight", "output_blocks.9.0.in_layers.2.bias", "output_blocks.9.0.emb_layers.1.weight", "output_blocks.9.0.emb_layers.1.bias", "output_blocks.9.0.out_layers.0.weight", "output_blocks.9.0.out_layers.0.bias", "output_blocks.9.0.out_layers.3.weight", "output_blocks.9.0.out_layers.3.bias", "output_blocks.9.0.skip_connection.weight", "output_blocks.9.0.skip_connection.bias", "output_blocks.9.1.norm.weight", "output_blocks.9.1.norm.bias", "output_blocks.9.1.proj_in.weight", "output_blocks.9.1.proj_in.bias", "output_blocks.9.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.9.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.9.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.9.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.9.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.9.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.9.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.9.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.9.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.9.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.9.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.9.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.9.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.9.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.9.1.transformer_blocks.0.norm1.weight", "output_blocks.9.1.transformer_blocks.0.norm1.bias", "output_blocks.9.1.transformer_blocks.0.norm2.weight", "output_blocks.9.1.transformer_blocks.0.norm2.bias", "output_blocks.9.1.transformer_blocks.0.norm3.weight", "output_blocks.9.1.transformer_blocks.0.norm3.bias", "output_blocks.9.1.proj_out.weight", "output_blocks.9.1.proj_out.bias", "output_blocks.10.0.in_layers.0.weight", "output_blocks.10.0.in_layers.0.bias", "output_blocks.10.0.in_layers.2.weight", "output_blocks.10.0.in_layers.2.bias", "output_blocks.10.0.emb_layers.1.weight", "output_blocks.10.0.emb_layers.1.bias", "output_blocks.10.0.out_layers.0.weight", "output_blocks.10.0.out_layers.0.bias", "output_blocks.10.0.out_layers.3.weight", "output_blocks.10.0.out_layers.3.bias", "output_blocks.10.0.skip_connection.weight", "output_blocks.10.0.skip_connection.bias", "output_blocks.10.1.norm.weight", "output_blocks.10.1.norm.bias", "output_blocks.10.1.proj_in.weight", "output_blocks.10.1.proj_in.bias", "output_blocks.10.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.10.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.10.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.10.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.10.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.10.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.10.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.10.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.10.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.10.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.10.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.10.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.10.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.10.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.10.1.transformer_blocks.0.norm1.weight", "output_blocks.10.1.transformer_blocks.0.norm1.bias", "output_blocks.10.1.transformer_blocks.0.norm2.weight", "output_blocks.10.1.transformer_blocks.0.norm2.bias", "output_blocks.10.1.transformer_blocks.0.norm3.weight", "output_blocks.10.1.transformer_blocks.0.norm3.bias", "output_blocks.10.1.proj_out.weight", "output_blocks.10.1.proj_out.bias", "output_blocks.11.0.in_layers.0.weight", "output_blocks.11.0.in_layers.0.bias", "output_blocks.11.0.in_layers.2.weight", "output_blocks.11.0.in_layers.2.bias", "output_blocks.11.0.emb_layers.1.weight", "output_blocks.11.0.emb_layers.1.bias", "output_blocks.11.0.out_layers.0.weight", "output_blocks.11.0.out_layers.0.bias", "output_blocks.11.0.out_layers.3.weight", "output_blocks.11.0.out_layers.3.bias", "output_blocks.11.0.skip_connection.weight", "output_blocks.11.0.skip_connection.bias", "output_blocks.11.1.norm.weight", "output_blocks.11.1.norm.bias", "output_blocks.11.1.proj_in.weight", "output_blocks.11.1.proj_in.bias", "output_blocks.11.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.11.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.11.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.11.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.11.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.11.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.11.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.11.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.11.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.11.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.11.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.11.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.11.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.11.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.11.1.transformer_blocks.0.norm1.weight", "output_blocks.11.1.transformer_blocks.0.norm1.bias", "output_blocks.11.1.transformer_blocks.0.norm2.weight", "output_blocks.11.1.transformer_blocks.0.norm2.bias", "output_blocks.11.1.transformer_blocks.0.norm3.weight", "output_blocks.11.1.transformer_blocks.0.norm3.bias", "output_blocks.11.1.proj_out.weight", "output_blocks.11.1.proj_out.bias", "out.0.weight", "out.0.bias", "out.2.weight", "out.2.bias"]
i2vgenxl/models/open_clip_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a78ef8e8c73fd0df621682e7a8e8eb36c6916cb3c16b291a082ecd52ab79cc4
3
+ size 3944692325
i2vgenxl/scheduler/scheduler_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "v_prediction",
12
+ "rescale_betas_zero_snr": true,
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": true,
15
+ "steps_offset": 1,
16
+ "thresholding": false,
17
+ "timestep_spacing": "leading",
18
+ "trained_betas": null
19
+ }
i2vgenxl/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "i2vgen-xl/text_encoder",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
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
+ }
i2vgenxl/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd94a7ea6922e8028227567fe14e04d2989eec31c482e0813e9006afea6637f1
3
+ size 1411983168
i2vgenxl/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
i2vgenxl/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
i2vgenxl/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 77,
27
+ "pad_token": "<|endoftext|>",
28
+ "tokenizer_class": "CLIPTokenizer",
29
+ "unk_token": "<|endoftext|>"
30
+ }
i2vgenxl/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
i2vgenxl/unet/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "I2VGenXLUNet",
3
+ "_diffusers_version": "0.26.1",
4
+ "_name_or_path": "i2vgen-xl/unet",
5
+ "attention_head_dim": 64,
6
+ "block_out_channels": [
7
+ 320,
8
+ 640,
9
+ 1280,
10
+ 1280
11
+ ],
12
+ "cross_attention_dim": 1024,
13
+ "down_block_types": [
14
+ "CrossAttnDownBlock3D",
15
+ "CrossAttnDownBlock3D",
16
+ "CrossAttnDownBlock3D",
17
+ "DownBlock3D"
18
+ ],
19
+ "in_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "num_attention_heads": 64,
23
+ "out_channels": 4,
24
+ "sample_size": 32,
25
+ "up_block_types": [
26
+ "UpBlock3D",
27
+ "CrossAttnUpBlock3D",
28
+ "CrossAttnUpBlock3D",
29
+ "CrossAttnUpBlock3D"
30
+ ]
31
+ }
i2vgenxl/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7c73b3ff159580a1a6535b1ccb473b09a2f40853c03f5d546db70632456ab8
3
+ size 5682063336
i2vgenxl/vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 4,
21
+ "layers_per_block": 2,
22
+ "norm_num_groups": 32,
23
+ "out_channels": 3,
24
+ "sample_size": 768,
25
+ "scaling_factor": 0.18125,
26
+ "up_block_types": [
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D"
31
+ ]
32
+ }
i2vgenxl/vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
3
+ size 334643268