Upload folder using huggingface_hub
Browse files- CLIP_projection/config.json +6 -0
- CLIP_projection/diffusion_pytorch_model.bin +3 -0
- image_encoder/config.json +23 -0
- image_encoder/pytorch_model.bin +3 -0
- model_index.json +33 -0
- scheduler/scheduler_config.json +20 -0
- unet/config.json +65 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +31 -0
- vae/diffusion_pytorch_model.bin +3 -0
CLIP_projection/config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "CLIPProjection",
|
3 |
+
"_diffusers_version": "0.18.2",
|
4 |
+
"in_channel": 1024,
|
5 |
+
"out_channel": 768
|
6 |
+
}
|
CLIP_projection/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:567a99c01ccb04ce2f0b56efa0d23ea6db316a718c660cb122bdb7962389a567
|
3 |
+
size 3155571
|
image_encoder/config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/clip-vit-large-patch14",
|
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": "bfloat16",
|
22 |
+
"transformers_version": "4.34.0"
|
23 |
+
}
|
image_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b007127192d023cbec39c96873e1dc6858f0be77b81fc70ac44bd321ee57202
|
3 |
+
size 608067629
|
model_index.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"CLIP_projection": [
|
3 |
+
"pipeline_zero1to3",
|
4 |
+
"CLIPProjection"
|
5 |
+
],
|
6 |
+
"_class_name": "Zero1to3StableDiffusionPipeline",
|
7 |
+
"_diffusers_version": "0.18.2",
|
8 |
+
"feature_extractor": [
|
9 |
+
null,
|
10 |
+
null
|
11 |
+
],
|
12 |
+
"image_encoder": [
|
13 |
+
"transformers",
|
14 |
+
"CLIPVisionModelWithProjection"
|
15 |
+
],
|
16 |
+
"requires_safety_checker": true,
|
17 |
+
"safety_checker": [
|
18 |
+
null,
|
19 |
+
null
|
20 |
+
],
|
21 |
+
"scheduler": [
|
22 |
+
"diffusers",
|
23 |
+
"DDPMScheduler"
|
24 |
+
],
|
25 |
+
"unet": [
|
26 |
+
"unet_2d_condition",
|
27 |
+
"UNet2DConditionModel"
|
28 |
+
],
|
29 |
+
"vae": [
|
30 |
+
"diffusers",
|
31 |
+
"AutoencoderKL"
|
32 |
+
]
|
33 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDPMScheduler",
|
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 |
+
"sample_max_value": 1.0,
|
13 |
+
"set_alpha_to_one": false,
|
14 |
+
"skip_prk_steps": true,
|
15 |
+
"steps_offset": 1,
|
16 |
+
"thresholding": false,
|
17 |
+
"timestep_spacing": "leading",
|
18 |
+
"trained_betas": null,
|
19 |
+
"variance_type": "fixed_small"
|
20 |
+
}
|
unet/config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.18.2",
|
4 |
+
"_name_or_path": "runwayml/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 |
+
"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 |
+
"dual_cross_attention": false,
|
31 |
+
"encoder_hid_dim": null,
|
32 |
+
"encoder_hid_dim_type": null,
|
33 |
+
"flip_sin_to_cos": true,
|
34 |
+
"freq_shift": 0,
|
35 |
+
"in_channels": 4,
|
36 |
+
"layers_per_block": 2,
|
37 |
+
"mid_block_only_cross_attention": null,
|
38 |
+
"mid_block_scale_factor": 1,
|
39 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
40 |
+
"norm_eps": 1e-05,
|
41 |
+
"norm_num_groups": 32,
|
42 |
+
"num_attention_heads": null,
|
43 |
+
"num_class_embeds": null,
|
44 |
+
"only_cross_attention": false,
|
45 |
+
"out_channels": 4,
|
46 |
+
"projection_class_embeddings_input_dim": null,
|
47 |
+
"resnet_out_scale_factor": 1.0,
|
48 |
+
"resnet_skip_time_act": false,
|
49 |
+
"resnet_time_scale_shift": "default",
|
50 |
+
"sample_size": 64,
|
51 |
+
"time_cond_proj_dim": null,
|
52 |
+
"time_embedding_act_fn": null,
|
53 |
+
"time_embedding_dim": null,
|
54 |
+
"time_embedding_type": "positional",
|
55 |
+
"timestep_post_act": null,
|
56 |
+
"transformer_layers_per_block": 1,
|
57 |
+
"up_block_types": [
|
58 |
+
"UpBlock2D",
|
59 |
+
"CrossAttnUpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"use_linear_projection": false
|
65 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:473743c93d5c21f1e1e1d5e66d007f7ec871e32ff887cab280e22251e8af4a64
|
3 |
+
size 3438375973
|
vae/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.18.2",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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 |
+
"in_channels": 3,
|
19 |
+
"latent_channels": 4,
|
20 |
+
"layers_per_block": 2,
|
21 |
+
"norm_num_groups": 32,
|
22 |
+
"out_channels": 3,
|
23 |
+
"sample_size": 512,
|
24 |
+
"scaling_factor": 0.18215,
|
25 |
+
"up_block_types": [
|
26 |
+
"UpDecoderBlock2D",
|
27 |
+
"UpDecoderBlock2D",
|
28 |
+
"UpDecoderBlock2D",
|
29 |
+
"UpDecoderBlock2D"
|
30 |
+
]
|
31 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ed683646d23a1f569ff9b8b40e923a82b53431e1b15f5eae61b54600767e2d2
|
3 |
+
size 167407857
|