Upload 18 files
Browse files- s1_pipe/feature_extractor/preprocessor_config.json +27 -0
- s1_pipe/image_encoder/config.json +23 -0
- s1_pipe/image_encoder/model.safetensors +3 -0
- s1_pipe/model_index.json +30 -0
- s1_pipe/scheduler/scheduler_config.json +15 -0
- s1_pipe/unet/config.json +73 -0
- s1_pipe/unet/diffusion_pytorch_model.safetensors +3 -0
- s1_pipe/vae/config.json +32 -0
- s1_pipe/vae/diffusion_pytorch_model.safetensors +3 -0
- s2_pipe/feature_extractor/preprocessor_config.json +27 -0
- s2_pipe/image_encoder/config.json +23 -0
- s2_pipe/image_encoder/model.safetensors +3 -0
- s2_pipe/model_index.json +25 -0
- s2_pipe/scheduler/scheduler_config.json +20 -0
- s2_pipe/unet/config.json +40 -0
- s2_pipe/unet/diffusion_pytorch_model.safetensors +3 -0
- s2_pipe/vae/config.json +24 -0
- s2_pipe/vae/diffusion_pytorch_model.safetensors +3 -0
s1_pipe/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 |
+
}
|
s1_pipe/image_encoder/config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/remote-home/pyt/sd-image-variations-diffusers",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPVisionModelWithProjection"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"dropout": 0.0,
|
8 |
+
"hidden_act": "quick_gelu",
|
9 |
+
"hidden_size": 1024,
|
10 |
+
"image_size": 224,
|
11 |
+
"initializer_factor": 1.0,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
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": 24,
|
19 |
+
"patch_size": 14,
|
20 |
+
"projection_dim": 768,
|
21 |
+
"torch_dtype": "float16",
|
22 |
+
"transformers_version": "4.37.1"
|
23 |
+
}
|
s1_pipe/image_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dd0c1777bb75e2e9b7aa29b799b3ee8ebaaaa731e2c471a9ec589f12542cce7
|
3 |
+
size 607980096
|
s1_pipe/model_index.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "MVDiffusionRefImagePipeline",
|
3 |
+
"_diffusers_version": "0.24.0",
|
4 |
+
"_name_or_path": "/remote-home/pyt/sd-image-variations-diffusers",
|
5 |
+
"feature_extractor": [
|
6 |
+
"transformers",
|
7 |
+
"CLIPImageProcessor"
|
8 |
+
],
|
9 |
+
"image_encoder": [
|
10 |
+
"transformers",
|
11 |
+
"CLIPVisionModelWithProjection"
|
12 |
+
],
|
13 |
+
"requires_safety_checker": true,
|
14 |
+
"safety_checker": [
|
15 |
+
null,
|
16 |
+
null
|
17 |
+
],
|
18 |
+
"scheduler": [
|
19 |
+
"diffusers",
|
20 |
+
"PNDMScheduler"
|
21 |
+
],
|
22 |
+
"unet": [
|
23 |
+
"models.unet_mv2d_condition",
|
24 |
+
"UNetMV2DConditionModel"
|
25 |
+
],
|
26 |
+
"vae": [
|
27 |
+
"diffusers",
|
28 |
+
"AutoencoderKL"
|
29 |
+
]
|
30 |
+
}
|
s1_pipe/scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.24.0",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"clip_sample": false,
|
8 |
+
"num_train_timesteps": 1000,
|
9 |
+
"prediction_type": "epsilon",
|
10 |
+
"set_alpha_to_one": false,
|
11 |
+
"skip_prk_steps": true,
|
12 |
+
"steps_offset": 1,
|
13 |
+
"timestep_spacing": "leading",
|
14 |
+
"trained_betas": null
|
15 |
+
}
|
s1_pipe/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNetMV2DConditionModel",
|
3 |
+
"_diffusers_version": "0.24.0",
|
4 |
+
"_name_or_path": "s1s2_1112222/checkpoint-40000",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": null,
|
9 |
+
"attention_head_dim": 8,
|
10 |
+
"block_out_channels": [
|
11 |
+
320,
|
12 |
+
640,
|
13 |
+
1280,
|
14 |
+
1280
|
15 |
+
],
|
16 |
+
"cd_attention_last": false,
|
17 |
+
"cd_attention_mid": true,
|
18 |
+
"center_input_sample": false,
|
19 |
+
"class_embed_type": "projection",
|
20 |
+
"class_embeddings_concat": false,
|
21 |
+
"conv_in_kernel": 3,
|
22 |
+
"conv_out_kernel": 3,
|
23 |
+
"cross_attention_dim": 768,
|
24 |
+
"cross_attention_norm": null,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlockMV2D",
|
27 |
+
"CrossAttnDownBlockMV2D",
|
28 |
+
"CrossAttnDownBlockMV2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 8,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlockMV2DCrossAttn",
|
42 |
+
"moe_mlp": false,
|
43 |
+
"multiview_attention": true,
|
44 |
+
"mvcd_attention": false,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"num_task": 2,
|
50 |
+
"num_views": 9,
|
51 |
+
"only_cross_attention": false,
|
52 |
+
"out_channels": 4,
|
53 |
+
"projection_class_embeddings_input_dim": 12,
|
54 |
+
"resnet_out_scale_factor": 1.0,
|
55 |
+
"resnet_skip_time_act": false,
|
56 |
+
"resnet_time_scale_shift": "default",
|
57 |
+
"sample_size": 32,
|
58 |
+
"sparse_mv_attention": false,
|
59 |
+
"time_cond_proj_dim": null,
|
60 |
+
"time_embedding_act_fn": null,
|
61 |
+
"time_embedding_dim": null,
|
62 |
+
"time_embedding_type": "positional",
|
63 |
+
"timestep_post_act": null,
|
64 |
+
"transformer_layers_per_block": 1,
|
65 |
+
"up_block_types": [
|
66 |
+
"UpBlock2D",
|
67 |
+
"CrossAttnUpBlockMV2D",
|
68 |
+
"CrossAttnUpBlockMV2D",
|
69 |
+
"CrossAttnUpBlockMV2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": false,
|
72 |
+
"use_linear_projection": false
|
73 |
+
}
|
s1_pipe/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4640ed32e1010be2d1eb86916d5e745c2b1f43ef57e025e35c2ae940f087c1bd
|
3 |
+
size 3643251840
|
s1_pipe/vae/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.24.0",
|
4 |
+
"_name_or_path": "/remote-home/pyt/sd-image-variations-diffusers",
|
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": 256,
|
25 |
+
"scaling_factor": 0.18215,
|
26 |
+
"up_block_types": [
|
27 |
+
"UpDecoderBlock2D",
|
28 |
+
"UpDecoderBlock2D",
|
29 |
+
"UpDecoderBlock2D",
|
30 |
+
"UpDecoderBlock2D"
|
31 |
+
]
|
32 |
+
}
|
s1_pipe/vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
|
3 |
+
size 167335342
|
s2_pipe/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 |
+
}
|
s2_pipe/image_encoder/config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
|
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": "float32",
|
22 |
+
"transformers_version": "4.37.2"
|
23 |
+
}
|
s2_pipe/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
|
s2_pipe/model_index.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableVideoDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.24.0",
|
4 |
+
"_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
|
5 |
+
"feature_extractor": [
|
6 |
+
"transformers",
|
7 |
+
"CLIPImageProcessor"
|
8 |
+
],
|
9 |
+
"image_encoder": [
|
10 |
+
"transformers",
|
11 |
+
"CLIPVisionModelWithProjection"
|
12 |
+
],
|
13 |
+
"scheduler": [
|
14 |
+
"diffusers",
|
15 |
+
"EulerDiscreteScheduler"
|
16 |
+
],
|
17 |
+
"unet": [
|
18 |
+
"models.unet_spatio_temporal_condition",
|
19 |
+
"UNetSpatioTemporalConditionModel"
|
20 |
+
],
|
21 |
+
"vae": [
|
22 |
+
"diffusers",
|
23 |
+
"AutoencoderKLTemporalDecoder"
|
24 |
+
]
|
25 |
+
}
|
s2_pipe/scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "EulerDiscreteScheduler",
|
3 |
+
"_diffusers_version": "0.24.0",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"clip_sample": false,
|
8 |
+
"interpolation_type": "linear",
|
9 |
+
"num_train_timesteps": 1000,
|
10 |
+
"prediction_type": "v_prediction",
|
11 |
+
"set_alpha_to_one": false,
|
12 |
+
"sigma_max": 700.0,
|
13 |
+
"sigma_min": 0.002,
|
14 |
+
"skip_prk_steps": true,
|
15 |
+
"steps_offset": 1,
|
16 |
+
"timestep_spacing": "leading",
|
17 |
+
"timestep_type": "continuous",
|
18 |
+
"trained_betas": null,
|
19 |
+
"use_karras_sigmas": true
|
20 |
+
}
|
s2_pipe/unet/config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNetSpatioTemporalConditionModel",
|
3 |
+
"_diffusers_version": "0.24.0",
|
4 |
+
"_name_or_path": "./s2/checkpoint-18000",
|
5 |
+
"addition_time_embed_dim": 256,
|
6 |
+
"block_out_channels": [
|
7 |
+
320,
|
8 |
+
640,
|
9 |
+
1280,
|
10 |
+
1280
|
11 |
+
],
|
12 |
+
"cross_attention_dim": 1024,
|
13 |
+
"down_block_types": [
|
14 |
+
"CrossAttnDownBlockSpatioTemporal",
|
15 |
+
"CrossAttnDownBlockSpatioTemporal",
|
16 |
+
"CrossAttnDownBlockSpatioTemporal",
|
17 |
+
"DownBlockSpatioTemporal"
|
18 |
+
],
|
19 |
+
"in_channels": 8,
|
20 |
+
"layers_per_block": 2,
|
21 |
+
"num_attention_heads": [
|
22 |
+
5,
|
23 |
+
10,
|
24 |
+
20,
|
25 |
+
20
|
26 |
+
],
|
27 |
+
"num_frames": 25,
|
28 |
+
"num_views": 9,
|
29 |
+
"out_channels": 4,
|
30 |
+
"projection_class_embeddings_input_dim": 768,
|
31 |
+
"projection_class_embeddings_input_dim_": 6,
|
32 |
+
"sample_size": 96,
|
33 |
+
"transformer_layers_per_block": 1,
|
34 |
+
"up_block_types": [
|
35 |
+
"UpBlockSpatioTemporal",
|
36 |
+
"CrossAttnUpBlockSpatioTemporal",
|
37 |
+
"CrossAttnUpBlockSpatioTemporal",
|
38 |
+
"CrossAttnUpBlockSpatioTemporal"
|
39 |
+
]
|
40 |
+
}
|
s2_pipe/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fdffd336fbcf85471e788059b8f3dc28ef021f635434c341980bf6fdd3188d8
|
3 |
+
size 6105277456
|
s2_pipe/vae/config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKLTemporalDecoder",
|
3 |
+
"_diffusers_version": "0.24.0",
|
4 |
+
"_name_or_path": "stabilityai/stable-video-diffusion-img2vid-xt",
|
5 |
+
"block_out_channels": [
|
6 |
+
128,
|
7 |
+
256,
|
8 |
+
512,
|
9 |
+
512
|
10 |
+
],
|
11 |
+
"down_block_types": [
|
12 |
+
"DownEncoderBlock2D",
|
13 |
+
"DownEncoderBlock2D",
|
14 |
+
"DownEncoderBlock2D",
|
15 |
+
"DownEncoderBlock2D"
|
16 |
+
],
|
17 |
+
"force_upcast": true,
|
18 |
+
"in_channels": 3,
|
19 |
+
"latent_channels": 4,
|
20 |
+
"layers_per_block": 2,
|
21 |
+
"out_channels": 3,
|
22 |
+
"sample_size": 768,
|
23 |
+
"scaling_factor": 0.18215
|
24 |
+
}
|
s2_pipe/vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d92aa595a53d9da9faf594f09910ee869d5d567c8bb0362d5095673c69997d6
|
3 |
+
size 391017740
|