clip_tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
clip_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
clip_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "do_lower_case": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 77,
22
+ "name_or_path": "openai/clip-vit-large-patch14",
23
+ "pad_token": "<|endoftext|>",
24
+ "special_tokens_map_file": "./special_tokens_map.json",
25
+ "tokenizer_class": "CLIPTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
clip_tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
image_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-base-patch32",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "quick_gelu",
9
+ "hidden_size": 768,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 12,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 12,
19
+ "patch_size": 32,
20
+ "projection_dim": 512,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.26.1"
23
+ }
image_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c14c7620d6f60372168b469b8dc9a0da10b30ba308b3499e687315a9cf0aa84
3
+ size 351463409
image_processor/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
+ }
model_index.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UniDiffuserPipeline",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "clip_tokenizer": [
5
+ "transformers",
6
+ "CLIPTokenizer"
7
+ ],
8
+ "image_encoder": [
9
+ "transformers",
10
+ "CLIPVisionModelWithProjection"
11
+ ],
12
+ "image_processor": [
13
+ "transformers",
14
+ "CLIPImageProcessor"
15
+ ],
16
+ "scheduler": [
17
+ "diffusers",
18
+ "DPMSolverMultistepScheduler"
19
+ ],
20
+ "text_decoder": [
21
+ "unidiffuser",
22
+ "UniDiffuserTextDecoder"
23
+ ],
24
+ "text_encoder": [
25
+ "transformers",
26
+ "CLIPTextModel"
27
+ ],
28
+ "text_tokenizer": [
29
+ "transformers",
30
+ "GPT2Tokenizer"
31
+ ],
32
+ "unet": [
33
+ "unidiffuser",
34
+ "UniDiffuserModel"
35
+ ],
36
+ "vae": [
37
+ "diffusers",
38
+ "AutoencoderKL"
39
+ ]
40
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DPMSolverMultistepScheduler",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "algorithm_type": "dpmsolver++",
5
+ "beta_end": 0.012,
6
+ "beta_schedule": "scaled_linear",
7
+ "beta_start": 0.00085,
8
+ "dynamic_thresholding_ratio": 0.995,
9
+ "lambda_min_clipped": -Infinity,
10
+ "lower_order_final": true,
11
+ "num_train_timesteps": 1000,
12
+ "prediction_type": "epsilon",
13
+ "sample_max_value": 1.0,
14
+ "solver_order": 3,
15
+ "solver_type": "midpoint",
16
+ "thresholding": false,
17
+ "trained_betas": null,
18
+ "use_karras_sigmas": false,
19
+ "variance_type": null
20
+ }
text_decoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UniDiffuserTextDecoder",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "activation_function": "gelu",
5
+ "attn_pdrop": 0.1,
6
+ "embd_pdrop": 0.1,
7
+ "initializer_range": 0.02,
8
+ "layer_norm_epsilon": 1e-05,
9
+ "n_embd": 768,
10
+ "n_head": 12,
11
+ "n_inner": 3072,
12
+ "n_layer": 12,
13
+ "n_positions": 1024,
14
+ "prefix_hidden_dim": 64,
15
+ "prefix_inner_dim": 768,
16
+ "prefix_length": 77,
17
+ "reorder_and_upcast_attn": false,
18
+ "resid_pdrop": 0.1,
19
+ "scale_attn_by_inverse_layer_idx": false,
20
+ "scale_attn_weights": true,
21
+ "use_cache": true,
22
+ "vocab_size": 50258
23
+ }
text_decoder/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8d2be17e1a581a8b04c298b76477673a42df5647bb9f4e685947cbab68f1c2f
3
+ size 510810305
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-large-patch14",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 768,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.26.1",
24
+ "vocab_size": 49408
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98124f3d5663b2f14ff08d4c29db93800622b4fcfa3d952bb6f9112f5d6dadd7
3
+ size 492307041
text_tokenizer/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|EOS|>": 50257
3
+ }
text_tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
text_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": "<|EOS|>",
10
+ "unk_token": {
11
+ "content": "<|endoftext|>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ }
text_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1024,
22
+ "name_or_path": "gpt2",
23
+ "pad_token": null,
24
+ "special_tokens_map_file": null,
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
text_tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UniDiffuserModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "activation_fn": "gelu",
5
+ "attention_bias": false,
6
+ "attention_head_dim": 64,
7
+ "block_type": "unidiffuser",
8
+ "clip_img_dim": 512,
9
+ "cross_attention_dim": null,
10
+ "dropout": 0.0,
11
+ "ff_final_dropout": true,
12
+ "in_channels": 4,
13
+ "norm_elementwise_affine": true,
14
+ "norm_num_groups": 32,
15
+ "norm_type": "layer_norm",
16
+ "num_attention_heads": 24,
17
+ "num_embeds_ada_norm": 1000,
18
+ "num_layers": 30,
19
+ "num_text_tokens": 77,
20
+ "num_vector_embeds": null,
21
+ "only_cross_attention": false,
22
+ "out_channels": 4,
23
+ "patch_size": 2,
24
+ "pre_layer_norm": false,
25
+ "sample_size": 64,
26
+ "text_dim": 64,
27
+ "upcast_attention": false,
28
+ "use_data_type_embedding": true,
29
+ "use_linear_projection": false,
30
+ "use_patch_pos_embed": false,
31
+ "use_timestep_embedding": false
32
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9307cd7aff6c6a22945c19723e0426f5631ebb31406d7d7021a2aa7127cc69fe
3
+ size 3810352317
vae/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.15.0.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": 256,
23
+ "scaling_factor": 0.18215,
24
+ "up_block_types": [
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D"
29
+ ]
30
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af27ea858349760ebe3311953e0bfe8d6fd257dc9537ae0b2b938c262132a2c6
3
+ size 334711857