Hugging Face's logo

benjamin-paine
/
champ

Diffusers
Safetensors
CHAMPPipeline
Model card Files Community
benjamin-paine commited on
Commit
6a6032e
•
1 Parent(s): f37bfe5

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. champ.fp16.safetensors +3 -0
  2. champ.safetensors +3 -0
  3. denoising_unet/config.json +68 -0
  4. denoising_unet/diffusion_pytorch_model.fp16.safetensors +3 -0
  5. denoising_unet/diffusion_pytorch_model.safetensors +3 -0
  6. guidance_encoder_depth/config.json +13 -0
  7. guidance_encoder_depth/diffusion_pytorch_model.fp16.safetensors +3 -0
  8. guidance_encoder_depth/diffusion_pytorch_model.safetensors +3 -0
  9. guidance_encoder_dwpose/config.json +13 -0
  10. guidance_encoder_dwpose/diffusion_pytorch_model.fp16.safetensors +3 -0
  11. guidance_encoder_dwpose/diffusion_pytorch_model.safetensors +3 -0
  12. guidance_encoder_normal/config.json +13 -0
  13. guidance_encoder_normal/diffusion_pytorch_model.fp16.safetensors +3 -0
  14. guidance_encoder_normal/diffusion_pytorch_model.safetensors +3 -0
  15. guidance_encoder_semantic_map/config.json +13 -0
  16. guidance_encoder_semantic_map/diffusion_pytorch_model.fp16.safetensors +3 -0
  17. guidance_encoder_semantic_map/diffusion_pytorch_model.safetensors +3 -0
  18. image_encoder/config.json +22 -0
  19. image_encoder/model.fp16.safetensors +3 -0
  20. image_encoder/model.safetensors +3 -0
  21. model_index.json +52 -0
  22. reference_unet/config.json +67 -0
  23. reference_unet/diffusion_pytorch_model.fp16.safetensors +3 -0
  24. reference_unet/diffusion_pytorch_model.safetensors +3 -0
  25. scheduler/scheduler_config.json +19 -0
  26. vae/config.json +31 -0
  27. vae/diffusion_pytorch_model.fp16.safetensors +3 -0
  28. vae/diffusion_pytorch_model.safetensors +3 -0
champ.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73411fd75ced03259d3d7170f433a9fc120c7c5a308c04c8d485e83594149dd
3
+ size 5153258872
champ.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b92712e47e3d001d4288e904f30d1db3a6d2ea9e560d01110f8dce0637382731
3
+ size 10306061292
denoising_unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet3DConditionModel",
3
+ "_diffusers_version": "0.26.1",
4
+ "act_fn": "silu",
5
+ "attention_head_dim": 8,
6
+ "block_out_channels": [
7
+ 320,
8
+ 640,
9
+ 1280,
10
+ 1280
11
+ ],
12
+ "center_input_sample": false,
13
+ "class_embed_type": null,
14
+ "cross_attention_dim": 768,
15
+ "down_block_types": [
16
+ "CrossAttnDownBlock3D",
17
+ "CrossAttnDownBlock3D",
18
+ "CrossAttnDownBlock3D",
19
+ "DownBlock3D"
20
+ ],
21
+ "downsample_padding": 1,
22
+ "dual_cross_attention": false,
23
+ "flip_sin_to_cos": true,
24
+ "freq_shift": 0,
25
+ "in_channels": 4,
26
+ "layers_per_block": 2,
27
+ "mid_block_scale_factor": 1,
28
+ "mid_block_type": "UNetMidBlock3DCrossAttn",
29
+ "motion_module_decoder_only": false,
30
+ "motion_module_kwargs": {
31
+ "attention_block_types": [
32
+ "Temporal_Self",
33
+ "Temporal_Self"
34
+ ],
35
+ "num_attention_heads": 8,
36
+ "num_transformer_block": 1,
37
+ "temporal_attention_dim_div": 1,
38
+ "temporal_position_encoding": true,
39
+ "temporal_position_encoding_max_len": 32
40
+ },
41
+ "motion_module_mid_block": true,
42
+ "motion_module_resolutions": [
43
+ 1,
44
+ 2,
45
+ 4,
46
+ 8
47
+ ],
48
+ "motion_module_type": "Vanilla",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_class_embeds": null,
52
+ "only_cross_attention": false,
53
+ "out_channels": 4,
54
+ "resnet_time_scale_shift": "default",
55
+ "sample_size": 64,
56
+ "unet_use_cross_frame_attention": false,
57
+ "unet_use_temporal_attention": false,
58
+ "up_block_types": [
59
+ "UpBlock3D",
60
+ "CrossAttnUpBlock3D",
61
+ "CrossAttnUpBlock3D",
62
+ "CrossAttnUpBlock3D"
63
+ ],
64
+ "upcast_attention": false,
65
+ "use_inflated_groupnorm": true,
66
+ "use_linear_projection": false,
67
+ "use_motion_module": true
68
+ }
denoising_unet/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a26878b1ae6d2529e845284969e37874ec0e75861ac1a76ecd055a85c781ba
3
+ size 2628056032
denoising_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e8766be70d68ebff80d768c1364fa7d0fdf49eedf7607bfa17dace8fdc36fa9
3
+ size 5255933640
guidance_encoder_depth/config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "GuidanceEncoder",
3
+ "_diffusers_version": "0.26.1",
4
+ "attention_num_heads": 8,
5
+ "block_out_channels": [
6
+ 16,
7
+ 32,
8
+ 96,
9
+ 256
10
+ ],
11
+ "guidance_embedding_channels": 320,
12
+ "guidance_input_channels": 3
13
+ }
guidance_encoder_depth/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ffafd70eb0ca3ae3c62d509e8713d8fd7f3563c0e36d2e9f6dfc7845e43b87
3
+ size 7681872
guidance_encoder_depth/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:426eb07118c1a17c6ccef67cedeb9c23cd511c90313c1bffa08ce9fbb139cf8f
3
+ size 15348280
guidance_encoder_dwpose/config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "GuidanceEncoder",
3
+ "_diffusers_version": "0.26.1",
4
+ "attention_num_heads": 8,
5
+ "block_out_channels": [
6
+ 16,
7
+ 32,
8
+ 96,
9
+ 256
10
+ ],
11
+ "guidance_embedding_channels": 320,
12
+ "guidance_input_channels": 3
13
+ }
guidance_encoder_dwpose/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16cd072dda84a6e9b1b17f04df6716eca25ef28fa5c48e9d3c6b3f5c151199fd
3
+ size 7681872
guidance_encoder_dwpose/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e529979cbe6cd729e35a73573cf1e84c429eac9663c29b12d42dc8e83d351fea
3
+ size 15348280
guidance_encoder_normal/config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "GuidanceEncoder",
3
+ "_diffusers_version": "0.26.1",
4
+ "attention_num_heads": 8,
5
+ "block_out_channels": [
6
+ 16,
7
+ 32,
8
+ 96,
9
+ 256
10
+ ],
11
+ "guidance_embedding_channels": 320,
12
+ "guidance_input_channels": 3
13
+ }
guidance_encoder_normal/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c8a6f6a60ec3c79b4dd50632c656b4016882f9d424da827361bcc4b34e17ea
3
+ size 7681872
guidance_encoder_normal/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3102ff7399163524eb55ec209bbec32688f5d63d37fd1bbae5b9b5eb835d404
3
+ size 15348280
guidance_encoder_semantic_map/config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "GuidanceEncoder",
3
+ "_diffusers_version": "0.26.1",
4
+ "attention_num_heads": 8,
5
+ "block_out_channels": [
6
+ 16,
7
+ 32,
8
+ 96,
9
+ 256
10
+ ],
11
+ "guidance_embedding_channels": 320,
12
+ "guidance_input_channels": 3
13
+ }
guidance_encoder_semantic_map/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b034ba5a8196c0d54e04018236859e69aa77103f8be56cccabc7556826a604d6
3
+ size 7681872
guidance_encoder_semantic_map/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e60a3a93ac8515e3c7a3b4675686d160d81bbd457a0eed184ecc8ce0183b26f
3
+ size 15348280
image_encoder/config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPVisionModelWithProjection"
4
+ ],
5
+ "attention_dropout": 0,
6
+ "dropout": 0,
7
+ "hidden_act": "quick_gelu",
8
+ "hidden_size": 1024,
9
+ "image_size": 224,
10
+ "initializer_factor": 1,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-05,
14
+ "model_type": "clip_vision_model",
15
+ "num_attention_heads": 16,
16
+ "num_channels": 3,
17
+ "num_hidden_layers": 24,
18
+ "patch_size": 14,
19
+ "projection_dim": 768,
20
+ "torch_dtype": "float16",
21
+ "transformers_version": "4.39.0"
22
+ }
image_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd0c1777bb75e2e9b7aa29b799b3ee8ebaaaa731e2c471a9ec589f12542cce7
3
+ size 607980096
image_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b33d2a3a643650857672e880ccf73adbaf114fbbadec36d142ee9d48af7e20
3
+ size 1215912728
model_index.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MultiGuidance2LongVideoPipeline",
3
+ "_diffusers_version": "0.26.1",
4
+ "denoising_unet": [
5
+ "champ.models.unet_3d_condition",
6
+ "UNet3DConditionModel"
7
+ ],
8
+ "guidance_encoder_depth": [
9
+ "champ.models.guidance_encoder",
10
+ "GuidanceEncoder"
11
+ ],
12
+ "guidance_encoder_dwpose": [
13
+ "champ.models.guidance_encoder",
14
+ "GuidanceEncoder"
15
+ ],
16
+ "guidance_encoder_normal": [
17
+ "champ.models.guidance_encoder",
18
+ "GuidanceEncoder"
19
+ ],
20
+ "guidance_encoder_semantic_map": [
21
+ "champ.models.guidance_encoder",
22
+ "GuidanceEncoder"
23
+ ],
24
+ "image_encoder": [
25
+ "transformers",
26
+ "CLIPVisionModelWithProjection"
27
+ ],
28
+ "image_proj_model": [
29
+ null,
30
+ null
31
+ ],
32
+ "reference_unet": [
33
+ "champ.models.unet_2d_condition",
34
+ "UNet2DConditionModel"
35
+ ],
36
+ "scheduler": [
37
+ "diffusers",
38
+ "DDIMScheduler"
39
+ ],
40
+ "text_encoder": [
41
+ null,
42
+ null
43
+ ],
44
+ "tokenizer": [
45
+ null,
46
+ null
47
+ ],
48
+ "vae": [
49
+ "diffusers",
50
+ "AutoencoderKL"
51
+ ]
52
+ }
reference_unet/config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.26.1",
4
+ "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": null,
8
+ "attention_head_dim": 8,
9
+ "attention_type": "default",
10
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "center_input_sample": false,
17
+ "class_embed_type": null,
18
+ "class_embeddings_concat": false,
19
+ "conv_in_kernel": 3,
20
+ "conv_out_kernel": 3,
21
+ "cross_attention_dim": 768,
22
+ "cross_attention_norm": null,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dropout": 0.0,
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
+ "reverse_transformer_layers_per_block": null,
52
+ "sample_size": 64,
53
+ "time_cond_proj_dim": null,
54
+ "time_embedding_act_fn": null,
55
+ "time_embedding_dim": null,
56
+ "time_embedding_type": "positional",
57
+ "timestep_post_act": null,
58
+ "transformer_layers_per_block": 1,
59
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "use_linear_projection": false
67
+ }
reference_unet/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e50564120586a35814027506028f149ed95dd25416145e9a62beacd6271b02ce
3
+ size 1719100656
reference_unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaa0516f44df87ad8d7c4dbc5cfeeba7860bfb9645b172cf4a44186393142680
3
+ size 3438118560
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.26.1",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "linear",
6
+ "beta_start": 0.00085,
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": "trailing",
18
+ "trained_betas": null
19
+ }
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.26.1",
4
+ "act_fn": "silu",
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
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 256,
24
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
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
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