Hugging Face's logo

bennyguo
/
zero123-xl-diffusers

Diffusers
Safetensors
Zero123Pipeline
Model card Files Community
2
bennyguo commited on
Commit
ae385ed
•
1 Parent(s): a392183

add zero123-xl diffusers weights

Browse files
Files changed (19) hide show
  1. clip_camera_projection/config.json +6 -0
  2. clip_camera_projection/diffusion_pytorch_model.fp16.safetensors +3 -0
  3. clip_camera_projection/diffusion_pytorch_model.fp16_ema.safetensors +3 -0
  4. clip_camera_projection/diffusion_pytorch_model.safetensors +3 -0
  5. feature_extractor/preprocessor_config.json +28 -0
  6. image_encoder/config.json +23 -0
  7. image_encoder/model.fp16.safetensors +3 -0
  8. image_encoder/model.fp16_ema.safetensors +3 -0
  9. image_encoder/model.safetensors +3 -0
  10. model_index.json +33 -0
  11. scheduler/scheduler_config.json +19 -0
  12. unet/config.json +64 -0
  13. unet/diffusion_pytorch_model.fp16.safetensors +3 -0
  14. unet/diffusion_pytorch_model.fp16_ema.safetensors +3 -0
  15. unet/diffusion_pytorch_model.safetensors +3 -0
  16. vae/config.json +30 -0
  17. vae/diffusion_pytorch_model.fp16.safetensors +3 -0
  18. vae/diffusion_pytorch_model.fp16_ema.safetensors +3 -0
  19. vae/diffusion_pytorch_model.safetensors +3 -0
clip_camera_projection/config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "CLIPCameraProjection",
3
+ "_diffusers_version": "0.18.2",
4
+ "additional_embeddings": 4,
5
+ "embedding_dim": 768
6
+ }
clip_camera_projection/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de49f3ac9d5b93f4ff521dda6c2ad5f9852c7a7f5e865b8dbebad7ec4bc6bf89
3
+ size 1187512
clip_camera_projection/diffusion_pytorch_model.fp16_ema.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de49f3ac9d5b93f4ff521dda6c2ad5f9852c7a7f5e865b8dbebad7ec4bc6bf89
3
+ size 1187512
clip_camera_projection/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3abdc72656e59a669bc5b570c10da2e9aa26c393cef600a5c827dbe62563b1fd
3
+ size 2374840
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPImageProcessor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
image_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lambdalabs/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": "float32",
22
+ "transformers_version": "4.30.2"
23
+ }
image_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0839dc3a0f2899f9b85df8cd64b8acd1a3303a95f73a895aced7c31aee7d80cf
3
+ size 607982256
image_encoder/model.fp16_ema.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0839dc3a0f2899f9b85df8cd64b8acd1a3303a95f73a895aced7c31aee7d80cf
3
+ size 607982256
image_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58ac58ff5110a60ce6a3ce28f89dc94dfb74ed88dd8a95fb72c7e3e80f2f780
3
+ size 1215914880
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Zero123Pipeline",
3
+ "_diffusers_version": "0.18.2",
4
+ "clip_camera_projection": [
5
+ "zero123",
6
+ "CLIPCameraProjection"
7
+ ],
8
+ "feature_extractor": [
9
+ "transformers",
10
+ "CLIPImageProcessor"
11
+ ],
12
+ "image_encoder": [
13
+ "transformers",
14
+ "CLIPVisionModelWithProjection"
15
+ ],
16
+ "requires_safety_checker": false,
17
+ "safety_checker": [
18
+ null,
19
+ null
20
+ ],
21
+ "scheduler": [
22
+ "diffusers",
23
+ "DDIMScheduler"
24
+ ],
25
+ "unet": [
26
+ "diffusers",
27
+ "UNet2DConditionModel"
28
+ ],
29
+ "vae": [
30
+ "diffusers",
31
+ "AutoencoderKL"
32
+ ]
33
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.18.2",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_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": "epsilon",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": false,
15
+ "steps_offset": 1,
16
+ "thresholding": false,
17
+ "timestep_spacing": "leading",
18
+ "trained_betas": null
19
+ }
unet/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.18.2",
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
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "class_embeddings_concat": false,
18
+ "conv_in_kernel": 3,
19
+ "conv_out_kernel": 3,
20
+ "cross_attention_dim": 768,
21
+ "cross_attention_norm": null,
22
+ "down_block_types": [
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "DownBlock2D"
27
+ ],
28
+ "downsample_padding": 1,
29
+ "dual_cross_attention": false,
30
+ "encoder_hid_dim": null,
31
+ "encoder_hid_dim_type": null,
32
+ "flip_sin_to_cos": true,
33
+ "freq_shift": 0,
34
+ "in_channels": 8,
35
+ "layers_per_block": 2,
36
+ "mid_block_only_cross_attention": null,
37
+ "mid_block_scale_factor": 1,
38
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
39
+ "norm_eps": 1e-05,
40
+ "norm_num_groups": 32,
41
+ "num_attention_heads": null,
42
+ "num_class_embeds": null,
43
+ "only_cross_attention": false,
44
+ "out_channels": 4,
45
+ "projection_class_embeddings_input_dim": null,
46
+ "resnet_out_scale_factor": 1.0,
47
+ "resnet_skip_time_act": false,
48
+ "resnet_time_scale_shift": "default",
49
+ "sample_size": 32,
50
+ "time_cond_proj_dim": null,
51
+ "time_embedding_act_fn": null,
52
+ "time_embedding_dim": null,
53
+ "time_embedding_type": "positional",
54
+ "timestep_post_act": null,
55
+ "transformer_layers_per_block": 1,
56
+ "up_block_types": [
57
+ "UpBlock2D",
58
+ "CrossAttnUpBlock2D",
59
+ "CrossAttnUpBlock2D",
60
+ "CrossAttnUpBlock2D"
61
+ ],
62
+ "upcast_attention": null,
63
+ "use_linear_projection": false
64
+ }
unet/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:281d8e647ae909d95eff11c094ae1ddccfdf0eaf7fc395c34fc675c4c25be0b1
3
+ size 1719148344
unet/diffusion_pytorch_model.fp16_ema.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5e327399abc3a6d54e89f16a10b728dfd2162b4fc70258dbf934859ff7520f
3
+ size 1719148344
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a96a481f4af8c59049bf31ccf1bd0b68855c469cc7be1ab36a844a919f83cc
3
+ size 3438213624
vae/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.18.2",
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
+ "in_channels": 3,
18
+ "latent_channels": 4,
19
+ "layers_per_block": 2,
20
+ "norm_num_groups": 32,
21
+ "out_channels": 3,
22
+ "sample_size": 256,
23
+ "scaling_factor": 0.18215,
24
+ "up_block_types": [
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D"
29
+ ]
30
+ }
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.fp16_ema.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