davidi-bria commited on
Commit
b679900
1 Parent(s): 10bced2
model_index.json DELETED
@@ -1,42 +0,0 @@
1
- {
2
- "_class_name": "StableDiffusionXLGaiaPipeline",
3
- "_diffusers_version": "0.25.0",
4
- "_name_or_path": "/mnt/models/tailored_generation_bria23/stable_diffusion_xl",
5
- "feature_extractor": [
6
- null,
7
- null
8
- ],
9
- "force_zeros_for_empty_prompt": true,
10
- "image_encoder": [
11
- null,
12
- null
13
- ],
14
- "scheduler": [
15
- "diffusers",
16
- "LCMScheduler"
17
- ],
18
- "text_encoder": [
19
- "transformers",
20
- "CLIPTextModel"
21
- ],
22
- "text_encoder_2": [
23
- "transformers",
24
- "CLIPTextModelWithProjection"
25
- ],
26
- "tokenizer": [
27
- "transformers",
28
- "CLIPTokenizer"
29
- ],
30
- "tokenizer_2": [
31
- "transformers",
32
- "CLIPTokenizer"
33
- ],
34
- "unet": [
35
- "diffusers",
36
- "UNet2DConditionModel"
37
- ],
38
- "vae": [
39
- "diffusers",
40
- "AutoencoderKL"
41
- ]
42
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
scheduler/scheduler_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "_class_name": "LCMScheduler",
3
- "_diffusers_version": "0.25.0",
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
- "original_inference_steps": 50,
12
- "prediction_type": "epsilon",
13
- "rescale_betas_zero_snr": false,
14
- "sample_max_value": 1.0,
15
- "set_alpha_to_one": true,
16
- "steps_offset": 1,
17
- "thresholding": false,
18
- "timestep_scaling": 10.0,
19
- "timestep_spacing": "linspace",
20
- "trained_betas": null
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
text_encoder/config.json DELETED
@@ -1,25 +0,0 @@
1
- {
2
- "_name_or_path": "/mnt/models/tailored_generation_bria23/stable_diffusion_xl/text_encoder",
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": "float16",
23
- "transformers_version": "4.40.1",
24
- "vocab_size": 49408
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
text_encoder/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
3
- size 246144152
 
 
 
 
text_encoder_2/config.json DELETED
@@ -1,25 +0,0 @@
1
- {
2
- "_name_or_path": "/mnt/models/tailored_generation_bria23/stable_diffusion_xl/text_encoder_2",
3
- "architectures": [
4
- "CLIPTextModelWithProjection"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 0,
8
- "dropout": 0.0,
9
- "eos_token_id": 2,
10
- "hidden_act": "gelu",
11
- "hidden_size": 1280,
12
- "initializer_factor": 1.0,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 5120,
15
- "layer_norm_eps": 1e-05,
16
- "max_position_embeddings": 77,
17
- "model_type": "clip_text_model",
18
- "num_attention_heads": 20,
19
- "num_hidden_layers": 32,
20
- "pad_token_id": 1,
21
- "projection_dim": 1280,
22
- "torch_dtype": "float16",
23
- "transformers_version": "4.40.1",
24
- "vocab_size": 49408
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
text_encoder_2/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
3
- size 1389382176
 
 
 
 
tokenizer/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer/tokenizer_config.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "49406": {
5
- "content": "<|startoftext|>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "49407": {
13
- "content": "<|endoftext|>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- }
20
- },
21
- "bos_token": "<|startoftext|>",
22
- "clean_up_tokenization_spaces": true,
23
- "do_lower_case": true,
24
- "eos_token": "<|endoftext|>",
25
- "errors": "replace",
26
- "model_max_length": 77,
27
- "pad_token": "<|endoftext|>",
28
- "tokenizer_class": "CLIPTokenizer",
29
- "unk_token": "<|endoftext|>"
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
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": "!",
17
- "unk_token": {
18
- "content": "<|endoftext|>",
19
- "lstrip": false,
20
- "normalized": true,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_2/tokenizer_config.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "!",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "49406": {
13
- "content": "<|startoftext|>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "49407": {
21
- "content": "<|endoftext|>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- }
28
- },
29
- "bos_token": "<|startoftext|>",
30
- "clean_up_tokenization_spaces": true,
31
- "do_lower_case": true,
32
- "eos_token": "<|endoftext|>",
33
- "errors": "replace",
34
- "model_max_length": 77,
35
- "pad_token": "!",
36
- "tokenizer_class": "CLIPTokenizer",
37
- "unk_token": "<|endoftext|>"
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_2/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
unet/config.json DELETED
@@ -1,73 +0,0 @@
1
- {
2
- "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.25.0",
4
- "_name_or_path": "/mnt/models/tailored_generation_bria23/stable_diffusion_xl/unet",
5
- "act_fn": "silu",
6
- "addition_embed_type": "text_time",
7
- "addition_embed_type_num_heads": 64,
8
- "addition_time_embed_dim": 256,
9
- "attention_head_dim": [
10
- 5,
11
- 10,
12
- 20
13
- ],
14
- "attention_type": "default",
15
- "block_out_channels": [
16
- 320,
17
- 640,
18
- 1280
19
- ],
20
- "center_input_sample": false,
21
- "class_embed_type": null,
22
- "class_embeddings_concat": false,
23
- "conv_in_kernel": 3,
24
- "conv_out_kernel": 3,
25
- "cross_attention_dim": 2048,
26
- "cross_attention_norm": null,
27
- "down_block_types": [
28
- "DownBlock2D",
29
- "CrossAttnDownBlock2D",
30
- "CrossAttnDownBlock2D"
31
- ],
32
- "downsample_padding": 1,
33
- "dropout": 0.0,
34
- "dual_cross_attention": false,
35
- "encoder_hid_dim": null,
36
- "encoder_hid_dim_type": null,
37
- "flip_sin_to_cos": true,
38
- "freq_shift": 0,
39
- "in_channels": 4,
40
- "layers_per_block": 2,
41
- "mid_block_only_cross_attention": null,
42
- "mid_block_scale_factor": 1,
43
- "mid_block_type": "UNetMidBlock2DCrossAttn",
44
- "norm_eps": 1e-05,
45
- "norm_num_groups": 32,
46
- "num_attention_heads": null,
47
- "num_class_embeds": null,
48
- "only_cross_attention": false,
49
- "out_channels": 4,
50
- "projection_class_embeddings_input_dim": 2816,
51
- "resnet_out_scale_factor": 1.0,
52
- "resnet_skip_time_act": false,
53
- "resnet_time_scale_shift": "default",
54
- "reverse_transformer_layers_per_block": null,
55
- "sample_size": 128,
56
- "time_cond_proj_dim": null,
57
- "time_embedding_act_fn": null,
58
- "time_embedding_dim": null,
59
- "time_embedding_type": "positional",
60
- "timestep_post_act": null,
61
- "transformer_layers_per_block": [
62
- 1,
63
- 2,
64
- 10
65
- ],
66
- "up_block_types": [
67
- "CrossAttnUpBlock2D",
68
- "CrossAttnUpBlock2D",
69
- "UpBlock2D"
70
- ],
71
- "upcast_attention": null,
72
- "use_linear_projection": true
73
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
unet/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:27f9c1b3e75f684cb024289fca1c088e7aacbb6c289aadfd567abf1920ec3feb
3
- size 5135149760
 
 
 
 
vae/config.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.25.0",
4
- "_name_or_path": "/mnt/models/tailored_generation_bria23/stable_diffusion_xl/vae",
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
- "force_upcast": true,
19
- "in_channels": 3,
20
- "latent_channels": 4,
21
- "layers_per_block": 2,
22
- "norm_num_groups": 32,
23
- "out_channels": 3,
24
- "sample_size": 1024,
25
- "scaling_factor": 0.13025,
26
- "up_block_types": [
27
- "UpDecoderBlock2D",
28
- "UpDecoderBlock2D",
29
- "UpDecoderBlock2D",
30
- "UpDecoderBlock2D"
31
- ]
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vae/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:13d8982a399565dd8fb3fbb4c3f534c720ee84a0eea03b25d797d2981ee54876
3
- size 313615452