Adding `diffusers` weights of this model
Browse filesThis PR adds fp32 and fp16 weights in PyTorch and safetensors format to Yntec/ThirdComing
- feature_extractor/preprocessor_config.json +17 -1
- model_index.json +8 -4
- scheduler/scheduler_config.json +4 -15
- text_encoder/config.json +2 -2
- text_encoder/model.fp16.safetensors +1 -1
- text_encoder/model.safetensors +1 -1
- tokenizer/special_tokens_map.json +28 -4
- tokenizer/tokenizer_config.json +3 -5
- unet/config.json +3 -2
- unet/diffusion_pytorch_model.fp16.safetensors +1 -1
- unet/diffusion_pytorch_model.safetensors +1 -1
- vae/config.json +3 -1
feature_extractor/preprocessor_config.json
CHANGED
@@ -1,4 +1,21 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"crop_size": {
|
3 |
"height": 224,
|
4 |
"width": 224
|
@@ -8,7 +25,6 @@
|
|
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,
|
|
|
1 |
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_center_crop",
|
8 |
+
"crop_size",
|
9 |
+
"do_rescale",
|
10 |
+
"rescale_factor",
|
11 |
+
"do_normalize",
|
12 |
+
"image_mean",
|
13 |
+
"image_std",
|
14 |
+
"do_convert_rgb",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
"crop_size": {
|
20 |
"height": 224,
|
21 |
"width": 224
|
|
|
25 |
"do_normalize": true,
|
26 |
"do_rescale": true,
|
27 |
"do_resize": true,
|
|
|
28 |
"image_mean": [
|
29 |
0.48145466,
|
30 |
0.4578275,
|
model_index.json
CHANGED
@@ -1,18 +1,22 @@
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
"CLIPFeatureExtractor"
|
7 |
],
|
8 |
-
"
|
9 |
-
"safety_checker": [
|
10 |
null,
|
11 |
null
|
12 |
],
|
|
|
|
|
|
|
|
|
|
|
13 |
"scheduler": [
|
14 |
"diffusers",
|
15 |
-
"
|
16 |
],
|
17 |
"text_encoder": [
|
18 |
"transformers",
|
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
"CLIPFeatureExtractor"
|
7 |
],
|
8 |
+
"image_encoder": [
|
|
|
9 |
null,
|
10 |
null
|
11 |
],
|
12 |
+
"requires_safety_checker": true,
|
13 |
+
"safety_checker": [
|
14 |
+
"stable_diffusion",
|
15 |
+
"StableDiffusionSafetyChecker"
|
16 |
+
],
|
17 |
"scheduler": [
|
18 |
"diffusers",
|
19 |
+
"PNDMScheduler"
|
20 |
],
|
21 |
"text_encoder": [
|
22 |
"transformers",
|
scheduler/scheduler_config.json
CHANGED
@@ -1,26 +1,15 @@
|
|
1 |
{
|
2 |
-
"_class_name": "
|
3 |
-
"_diffusers_version": "0.
|
4 |
-
|
5 |
"beta_end": 0.012,
|
6 |
"beta_schedule": "scaled_linear",
|
7 |
"beta_start": 0.00085,
|
8 |
"clip_sample": false,
|
9 |
-
"clip_sample_range": 1.0,
|
10 |
-
"dynamic_thresholding_ratio": 0.995,
|
11 |
-
|
12 |
-
|
13 |
"num_train_timesteps": 1000,
|
14 |
"prediction_type": "epsilon",
|
15 |
-
"rescale_betas_zero_snr": false,
|
16 |
-
"sample_max_value": 1.0,
|
17 |
"set_alpha_to_one": false,
|
18 |
-
|
19 |
-
|
20 |
"steps_offset": 1,
|
21 |
-
"thresholding": false,
|
22 |
"timestep_spacing": "leading",
|
23 |
"trained_betas": null
|
24 |
-
|
25 |
-
|
26 |
-
}
|
|
|
1 |
{
|
2 |
+
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.28.0.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 |
"timestep_spacing": "leading",
|
14 |
"trained_betas": null
|
15 |
+
}
|
|
|
|
text_encoder/config.json
CHANGED
@@ -18,7 +18,7 @@
|
|
18 |
"num_hidden_layers": 12,
|
19 |
"pad_token_id": 1,
|
20 |
"projection_dim": 768,
|
21 |
-
"torch_dtype": "
|
22 |
-
"transformers_version": "4.
|
23 |
"vocab_size": 49408
|
24 |
}
|
|
|
18 |
"num_hidden_layers": 12,
|
19 |
"pad_token_id": 1,
|
20 |
"projection_dim": 768,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.41.1",
|
23 |
"vocab_size": 49408
|
24 |
}
|
text_encoder/model.fp16.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 492265168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f38b9239bea0e443f3e903e0b0b7bebb16531822cccf397702149ab25e2c934
|
3 |
size 492265168
|
text_encoder/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 492265168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f38b9239bea0e443f3e903e0b0b7bebb16531822cccf397702149ab25e2c934
|
3 |
size 492265168
|
tokenizer/special_tokens_map.json
CHANGED
@@ -1,6 +1,30 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
|
|
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": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
}
|
tokenizer/tokenizer_config.json
CHANGED
@@ -7,7 +7,7 @@
|
|
7 |
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
-
"special":
|
11 |
},
|
12 |
"49407": {
|
13 |
"content": "<|endoftext|>",
|
@@ -15,10 +15,9 @@
|
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
-
"special":
|
19 |
}
|
20 |
},
|
21 |
-
"additional_special_tokens": [],
|
22 |
"bos_token": "<|startoftext|>",
|
23 |
"clean_up_tokenization_spaces": true,
|
24 |
"do_lower_case": true,
|
@@ -27,6 +26,5 @@
|
|
27 |
"model_max_length": 77,
|
28 |
"pad_token": "<|endoftext|>",
|
29 |
"tokenizer_class": "CLIPTokenizer",
|
30 |
-
"tokenizer_file": "/home/user/.cache/huggingface/hub/models--openai--clip-vit-large-patch14/snapshots/32bd64288804d66eefd0ccbe215aa642df71cc41/tokenizer.json",
|
31 |
"unk_token": "<|endoftext|>"
|
32 |
-
}
|
|
|
7 |
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
+
"special": true
|
11 |
},
|
12 |
"49407": {
|
13 |
"content": "<|endoftext|>",
|
|
|
15 |
"normalized": false,
|
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,
|
|
|
26 |
"model_max_length": 77,
|
27 |
"pad_token": "<|endoftext|>",
|
28 |
"tokenizer_class": "CLIPTokenizer",
|
|
|
29 |
"unk_token": "<|endoftext|>"
|
30 |
+
}
|
unet/config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"act_fn": "silu",
|
5 |
"addition_embed_type": null,
|
6 |
"addition_embed_type_num_heads": 64,
|
@@ -48,6 +48,7 @@
|
|
48 |
"resnet_out_scale_factor": 1.0,
|
49 |
"resnet_skip_time_act": false,
|
50 |
"resnet_time_scale_shift": "default",
|
|
|
51 |
"sample_size": 96,
|
52 |
"time_cond_proj_dim": null,
|
53 |
"time_embedding_act_fn": null,
|
@@ -63,4 +64,4 @@
|
|
63 |
],
|
64 |
"upcast_attention": null,
|
65 |
"use_linear_projection": false
|
66 |
-
}
|
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
4 |
"act_fn": "silu",
|
5 |
"addition_embed_type": null,
|
6 |
"addition_embed_type_num_heads": 64,
|
|
|
48 |
"resnet_out_scale_factor": 1.0,
|
49 |
"resnet_skip_time_act": false,
|
50 |
"resnet_time_scale_shift": "default",
|
51 |
+
"reverse_transformer_layers_per_block": null,
|
52 |
"sample_size": 96,
|
53 |
"time_cond_proj_dim": null,
|
54 |
"time_embedding_act_fn": null,
|
|
|
64 |
],
|
65 |
"upcast_attention": null,
|
66 |
"use_linear_projection": false
|
67 |
+
}
|
unet/diffusion_pytorch_model.fp16.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3438167536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97d40ec87500d37fdf0e371b4b35435806b37f5ac18c151cac3d116d534d8782
|
3 |
size 3438167536
|
unet/diffusion_pytorch_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3438167536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97d40ec87500d37fdf0e371b4b35435806b37f5ac18c151cac3d116d534d8782
|
3 |
size 3438167536
|
vae/config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"act_fn": "silu",
|
5 |
"block_out_channels": [
|
6 |
128,
|
@@ -17,6 +17,8 @@
|
|
17 |
"force_upcast": true,
|
18 |
"in_channels": 3,
|
19 |
"latent_channels": 4,
|
|
|
|
|
20 |
"layers_per_block": 2,
|
21 |
"norm_num_groups": 32,
|
22 |
"out_channels": 3,
|
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
4 |
"act_fn": "silu",
|
5 |
"block_out_channels": [
|
6 |
128,
|
|
|
17 |
"force_upcast": true,
|
18 |
"in_channels": 3,
|
19 |
"latent_channels": 4,
|
20 |
+
"latents_mean": null,
|
21 |
+
"latents_std": null,
|
22 |
"layers_per_block": 2,
|
23 |
"norm_num_groups": 32,
|
24 |
"out_channels": 3,
|