feat: added model
Browse files
README.md
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: bsd-3-clause
|
3 |
+
---
|
4 |
+
Download MagicAnimate checkpoints by:
|
5 |
+
```bash
|
6 |
+
git lfs clone https://huggingface.co/zcxu-eric/MagicAnimate
|
7 |
+
```
|
appearance_encoder/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AppearanceEncoderModel",
|
3 |
+
"_diffusers_version": "0.21.4",
|
4 |
+
"_name_or_path": "pretrained_models/StableDiffusion/stable-diffusion-v1-5",
|
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 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": null,
|
33 |
+
"encoder_hid_dim_type": null,
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 4,
|
37 |
+
"layers_per_block": 2,
|
38 |
+
"mid_block_only_cross_attention": null,
|
39 |
+
"mid_block_scale_factor": 1,
|
40 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
41 |
+
"norm_eps": 1e-05,
|
42 |
+
"norm_num_groups": 32,
|
43 |
+
"num_attention_heads": null,
|
44 |
+
"num_class_embeds": null,
|
45 |
+
"only_cross_attention": false,
|
46 |
+
"out_channels": 4,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 64,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"transformer_layers_per_block": 1,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": false,
|
65 |
+
"use_linear_projection": false
|
66 |
+
}
|
appearance_encoder/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb2e8f281d73eff5f9b7f0c94118496607cf5f29fc5b56535a19a8b68e79b619
|
3 |
+
size 3428346912
|
densepose_controlnet/config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.21.4",
|
4 |
+
"_name_or_path": "pretrained_models/ControlNet/laion_plus_human_densepose_controlnet/checkpoint-14000/controlnet",
|
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 |
+
"class_embed_type": null,
|
17 |
+
"conditioning_channels": 3,
|
18 |
+
"conditioning_embedding_out_channels": [
|
19 |
+
16,
|
20 |
+
32,
|
21 |
+
96,
|
22 |
+
256
|
23 |
+
],
|
24 |
+
"controlnet_conditioning_channel_order": "rgb",
|
25 |
+
"cross_attention_dim": 768,
|
26 |
+
"down_block_types": [
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"DownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"global_pool_conditions": false,
|
38 |
+
"in_channels": 4,
|
39 |
+
"layers_per_block": 2,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"norm_eps": 1e-05,
|
42 |
+
"norm_num_groups": 32,
|
43 |
+
"num_attention_heads": null,
|
44 |
+
"num_class_embeds": null,
|
45 |
+
"only_cross_attention": false,
|
46 |
+
"projection_class_embeddings_input_dim": null,
|
47 |
+
"resnet_time_scale_shift": "default",
|
48 |
+
"transformer_layers_per_block": 1,
|
49 |
+
"upcast_attention": false,
|
50 |
+
"use_linear_projection": false
|
51 |
+
}
|
densepose_controlnet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5e06b41bd614e84eba294ebf2fa868ef31ffc88fca33987938fde3ec0eb67a4
|
3 |
+
size 1445157120
|
temporal_attention/temporal_attention.ckpt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e14b488d09569ddf5524cf6d671413b6fa6cf13ba2b1f304e5e965d2b997125
|
3 |
+
size 5110608419
|