patrickvonplaten commited on
Commit
f199dc0
1 Parent(s): aee33aa

add diffusers weights

Browse files
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 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PaintByExampleImageEncoder"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dropout": 0.0,
7
+ "hidden_act": "quick_gelu",
8
+ "hidden_size": 1024,
9
+ "image_size": 224,
10
+ "initializer_factor": 1.0,
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": "float32",
21
+ "transformers_version": "4.25.0.dev0"
22
+ }
image_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296d26d0c844328727c58870e169183c0d23a6d82ecd3467a8484610f3be6146
3
+ size 1467961031
model.ckpt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfe1becd255dfd8aee990faef838087ded20da406afe3bd73a585423afaa0dde
3
- size 5241118218
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8d93b5d3870fc918fddfeffdb44c36912d398b66ad05e6197c162e65940e505
3
+ size 12628030792
model_index.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PaintByExamplePipeline",
3
+ "_diffusers_version": "0.10.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPImageProcessor"
7
+ ],
8
+ "image_encoder": [
9
+ "paint_by_example",
10
+ "PaintByExampleImageEncoder"
11
+ ],
12
+ "requires_safety_checker": false,
13
+ "safety_checker": [
14
+ null,
15
+ null
16
+ ],
17
+ "scheduler": [
18
+ "diffusers",
19
+ "PNDMScheduler"
20
+ ],
21
+ "unet": [
22
+ "diffusers",
23
+ "UNet2DConditionModel"
24
+ ],
25
+ "vae": [
26
+ "diffusers",
27
+ "AutoencoderKL"
28
+ ]
29
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.10.0.dev0",
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
+ "trained_betas": null
14
+ }
unet/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.10.0.dev0",
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
+ "cross_attention_dim": 768,
14
+ "down_block_types": [
15
+ "CrossAttnDownBlock2D",
16
+ "CrossAttnDownBlock2D",
17
+ "CrossAttnDownBlock2D",
18
+ "DownBlock2D"
19
+ ],
20
+ "downsample_padding": 1,
21
+ "dual_cross_attention": false,
22
+ "flip_sin_to_cos": true,
23
+ "freq_shift": 0,
24
+ "in_channels": 9,
25
+ "layers_per_block": 2,
26
+ "mid_block_scale_factor": 1,
27
+ "norm_eps": 1e-05,
28
+ "norm_num_groups": 32,
29
+ "num_class_embeds": null,
30
+ "only_cross_attention": false,
31
+ "out_channels": 4,
32
+ "sample_size": 64,
33
+ "up_block_types": [
34
+ "UpBlock2D",
35
+ "CrossAttnUpBlock2D",
36
+ "CrossAttnUpBlock2D",
37
+ "CrossAttnUpBlock2D"
38
+ ],
39
+ "use_linear_projection": false
40
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2020aa8102bd6ea977738454f87d8e08483271469bfa1ebd1b62534f0cf7d371
3
+ size 3438412325
vae/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.10.0.dev0",
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": 512,
23
+ "up_block_types": [
24
+ "UpDecoderBlock2D",
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D"
28
+ ]
29
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b134cded8eb78b184aefb8805b6b572f36fa77b255c483665dda931fa0130c5
3
+ size 334707217