Hugging Face's logo

OpenPathAI
/
Orbit-1.2-image

Diffusers
Safetensors
StableDiffusionInstructPix2PixPipeline
Model card Files
xet
 Community
titanthree commited on
Commit
8d9780e
·
verified ·
1 Parent(s): 8aaf8de

Delete model_weights

Browse files
Files changed (13) hide show
  1. model_weights/feature_extractor/preprocessor_config.json +0 -27
  2. model_weights/model_index.json +0 -38
  3. model_weights/safety_checker/config.json +0 -82
  4. model_weights/safety_checker/model.safetensors +0 -3
  5. model_weights/scheduler/scheduler_config.json +0 -23
  6. model_weights/text_encoder/config.json +0 -24
  7. model_weights/text_encoder/model.safetensors +0 -3
  8. model_weights/tokenizer/tokenizer.json +0 -0
  9. model_weights/tokenizer/tokenizer_config.json +0 -13
  10. model_weights/unet/config.json +0 -68
  11. model_weights/unet/diffusion_pytorch_model.safetensors +0 -3
  12. model_weights/vae/config.json +0 -38
  13. model_weights/vae/diffusion_pytorch_model.safetensors +0 -3
model_weights/feature_extractor/preprocessor_config.json DELETED
@@ -1,27 +0,0 @@
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
- "image_mean": [
12
- 0.48145466,
13
- 0.4578275,
14
- 0.40821073
15
- ],
16
- "image_processor_type": "CLIPImageProcessor",
17
- "image_std": [
18
- 0.26862954,
19
- 0.26130258,
20
- 0.27577711
21
- ],
22
- "resample": 3,
23
- "rescale_factor": 0.00392156862745098,
24
- "size": {
25
- "shortest_edge": 224
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_weights/model_index.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "_class_name": "StableDiffusionInstructPix2PixPipeline",
3
- "_diffusers_version": "0.37.1",
4
- "_name_or_path": "timbrooks/instruct-pix2pix",
5
- "feature_extractor": [
6
- "transformers",
7
- "CLIPImageProcessor"
8
- ],
9
- "image_encoder": [
10
- null,
11
- null
12
- ],
13
- "requires_safety_checker": false,
14
- "safety_checker": [
15
- "stable_diffusion",
16
- "StableDiffusionSafetyChecker"
17
- ],
18
- "scheduler": [
19
- "diffusers",
20
- "EulerAncestralDiscreteScheduler"
21
- ],
22
- "text_encoder": [
23
- "transformers",
24
- "CLIPTextModel"
25
- ],
26
- "tokenizer": [
27
- "transformers",
28
- "CLIPTokenizer"
29
- ],
30
- "unet": [
31
- "diffusers",
32
- "UNet2DConditionModel"
33
- ],
34
- "vae": [
35
- "diffusers",
36
- "AutoencoderKL"
37
- ]
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_weights/safety_checker/config.json DELETED
@@ -1,82 +0,0 @@
1
- {
2
- "architectures": [
3
- "StableDiffusionSafetyChecker"
4
- ],
5
- "dtype": "float16",
6
- "initializer_factor": 1.0,
7
- "logit_scale_init_value": 2.6592,
8
- "model_type": "clip",
9
- "projection_dim": 768,
10
- "text_config": {
11
- "add_cross_attention": false,
12
- "attention_dropout": 0.0,
13
- "bos_token_id": 49406,
14
- "cross_attention_hidden_size": null,
15
- "decoder_start_token_id": null,
16
- "dropout": 0.0,
17
- "dtype": "float16",
18
- "eos_token_id": 49407,
19
- "finetuning_task": null,
20
- "hidden_act": "quick_gelu",
21
- "hidden_size": 768,
22
- "initializer_factor": 1.0,
23
- "initializer_range": 0.02,
24
- "intermediate_size": 3072,
25
- "is_decoder": false,
26
- "layer_norm_eps": 1e-05,
27
- "max_position_embeddings": 77,
28
- "model_type": "clip_text_model",
29
- "num_attention_heads": 12,
30
- "num_hidden_layers": 12,
31
- "pad_token_id": 1,
32
- "prefix": null,
33
- "projection_dim": 512,
34
- "pruned_heads": {},
35
- "sep_token_id": null,
36
- "task_specific_params": null,
37
- "tf_legacy_loss": false,
38
- "tie_encoder_decoder": false,
39
- "tie_word_embeddings": true,
40
- "tokenizer_class": null,
41
- "torchscript": false,
42
- "use_bfloat16": false,
43
- "vocab_size": 49408
44
- },
45
- "transformers_version": "5.0.0",
46
- "vision_config": {
47
- "add_cross_attention": false,
48
- "attention_dropout": 0.0,
49
- "bos_token_id": null,
50
- "cross_attention_hidden_size": null,
51
- "decoder_start_token_id": null,
52
- "dropout": 0.0,
53
- "dtype": "float16",
54
- "eos_token_id": null,
55
- "finetuning_task": null,
56
- "hidden_act": "quick_gelu",
57
- "hidden_size": 1024,
58
- "image_size": 224,
59
- "initializer_factor": 1.0,
60
- "initializer_range": 0.02,
61
- "intermediate_size": 4096,
62
- "is_decoder": false,
63
- "layer_norm_eps": 1e-05,
64
- "model_type": "clip_vision_model",
65
- "num_attention_heads": 16,
66
- "num_channels": 3,
67
- "num_hidden_layers": 24,
68
- "pad_token_id": null,
69
- "patch_size": 14,
70
- "prefix": null,
71
- "projection_dim": 512,
72
- "pruned_heads": {},
73
- "sep_token_id": null,
74
- "task_specific_params": null,
75
- "tf_legacy_loss": false,
76
- "tie_encoder_decoder": false,
77
- "tie_word_embeddings": true,
78
- "tokenizer_class": null,
79
- "torchscript": false,
80
- "use_bfloat16": false
81
- }
82
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_weights/safety_checker/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:57ecdfa243b170f9b4cb3eefaf0f64552ef78fc0bf0eb1c5b9675308447184f6
3
- size 608016280
 
 
 
 
model_weights/scheduler/scheduler_config.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "_class_name": "EulerAncestralDiscreteScheduler",
3
- "_diffusers_version": "0.37.1",
4
- "algorithm_type": "dpmsolver++",
5
- "beta_end": 0.012,
6
- "beta_schedule": "scaled_linear",
7
- "beta_start": 0.00085,
8
- "clip_sample": false,
9
- "dynamic_thresholding_ratio": 0.995,
10
- "lower_order_final": true,
11
- "num_train_timesteps": 1000,
12
- "prediction_type": "epsilon",
13
- "rescale_betas_zero_snr": false,
14
- "sample_max_value": 1.0,
15
- "set_alpha_to_one": false,
16
- "skip_prk_steps": true,
17
- "solver_order": 2,
18
- "solver_type": "midpoint",
19
- "steps_offset": 1,
20
- "thresholding": false,
21
- "timestep_spacing": "linspace",
22
- "trained_betas": null
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_weights/text_encoder/config.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "architectures": [
3
- "CLIPTextModel"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 0,
7
- "dropout": 0.0,
8
- "dtype": "float16",
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
- "transformers_version": "5.0.0",
23
- "vocab_size": 49408
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_weights/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
 
 
 
 
model_weights/tokenizer/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
model_weights/tokenizer/tokenizer_config.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "backend": "tokenizers",
4
- "bos_token": "<|startoftext|>",
5
- "do_lower_case": true,
6
- "eos_token": "<|endoftext|>",
7
- "errors": "replace",
8
- "is_local": true,
9
- "model_max_length": 77,
10
- "pad_token": "<|endoftext|>",
11
- "tokenizer_class": "CLIPTokenizer",
12
- "unk_token": "<|endoftext|>"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_weights/unet/config.json DELETED
@@ -1,68 +0,0 @@
1
- {
2
- "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.37.1",
4
- "_name_or_path": "/root/.cache/huggingface/hub/models--timbrooks--instruct-pix2pix/snapshots/31519b5cb02a7fd89b906d88731cd4d6a7bbf88d/unet",
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
- "attention_type": "default",
11
- "block_out_channels": [
12
- 320,
13
- 640,
14
- 1280,
15
- 1280
16
- ],
17
- "center_input_sample": false,
18
- "class_embed_type": null,
19
- "class_embeddings_concat": false,
20
- "conv_in_kernel": 3,
21
- "conv_out_kernel": 3,
22
- "cross_attention_dim": 768,
23
- "cross_attention_norm": null,
24
- "down_block_types": [
25
- "CrossAttnDownBlock2D",
26
- "CrossAttnDownBlock2D",
27
- "CrossAttnDownBlock2D",
28
- "DownBlock2D"
29
- ],
30
- "downsample_padding": 1,
31
- "dropout": 0.0,
32
- "dual_cross_attention": false,
33
- "encoder_hid_dim": null,
34
- "encoder_hid_dim_type": null,
35
- "flip_sin_to_cos": true,
36
- "freq_shift": 0,
37
- "in_channels": 8,
38
- "layers_per_block": 2,
39
- "mid_block_only_cross_attention": null,
40
- "mid_block_scale_factor": 1,
41
- "mid_block_type": "UNetMidBlock2DCrossAttn",
42
- "norm_eps": 1e-05,
43
- "norm_num_groups": 32,
44
- "num_attention_heads": null,
45
- "num_class_embeds": null,
46
- "only_cross_attention": false,
47
- "out_channels": 4,
48
- "projection_class_embeddings_input_dim": null,
49
- "resnet_out_scale_factor": 1.0,
50
- "resnet_skip_time_act": false,
51
- "resnet_time_scale_shift": "default",
52
- "reverse_transformer_layers_per_block": null,
53
- "sample_size": 64,
54
- "time_cond_proj_dim": null,
55
- "time_embedding_act_fn": null,
56
- "time_embedding_dim": null,
57
- "time_embedding_type": "positional",
58
- "timestep_post_act": null,
59
- "transformer_layers_per_block": 1,
60
- "up_block_types": [
61
- "UpBlock2D",
62
- "CrossAttnUpBlock2D",
63
- "CrossAttnUpBlock2D",
64
- "CrossAttnUpBlock2D"
65
- ],
66
- "upcast_attention": false,
67
- "use_linear_projection": false
68
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_weights/unet/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfe7553da633b94b327e111b7e8f3373e199ddeeafeb2eeb0817888ced0f4995
3
- size 1719148344
 
 
 
 
model_weights/vae/config.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.37.1",
4
- "_name_or_path": "/root/.cache/huggingface/hub/models--timbrooks--instruct-pix2pix/snapshots/31519b5cb02a7fd89b906d88731cd4d6a7bbf88d/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
- "latents_mean": null,
22
- "latents_std": null,
23
- "layers_per_block": 2,
24
- "mid_block_add_attention": true,
25
- "norm_num_groups": 32,
26
- "out_channels": 3,
27
- "sample_size": 512,
28
- "scaling_factor": 0.18215,
29
- "shift_factor": null,
30
- "up_block_types": [
31
- "UpDecoderBlock2D",
32
- "UpDecoderBlock2D",
33
- "UpDecoderBlock2D",
34
- "UpDecoderBlock2D"
35
- ],
36
- "use_post_quant_conv": true,
37
- "use_quant_conv": true
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_weights/vae/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
3
- size 167335342