lodestones
commited on
Commit
•
9f1325b
1
Parent(s):
1928af6
epoch 27
Browse files- model_index.json +7 -6
- scheduler/scheduler_config.json +8 -4
- text_encoder/config.json +2 -2
- text_encoder/pytorch_model.bin +1 -1
- tokenizer/tokenizer_config.json +1 -2
- unet/config.json +22 -2
- unet/diffusion_pytorch_model.bin +1 -1
- vae/config.json +3 -2
model_index.json
CHANGED
@@ -1,21 +1,22 @@
|
|
1 |
{
|
2 |
-
"_class_name": "
|
3 |
-
"_diffusers_version": "0.15.0
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
"CLIPFeatureExtractor"
|
7 |
],
|
|
|
8 |
"safety_checker": [
|
9 |
null,
|
10 |
null
|
11 |
],
|
12 |
"scheduler": [
|
13 |
"diffusers",
|
14 |
-
"
|
15 |
],
|
16 |
"text_encoder": [
|
17 |
"transformers",
|
18 |
-
"
|
19 |
],
|
20 |
"tokenizer": [
|
21 |
"transformers",
|
@@ -23,10 +24,10 @@
|
|
23 |
],
|
24 |
"unet": [
|
25 |
"diffusers",
|
26 |
-
"
|
27 |
],
|
28 |
"vae": [
|
29 |
"diffusers",
|
30 |
-
"
|
31 |
]
|
32 |
}
|
|
|
1 |
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.15.0",
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
"CLIPFeatureExtractor"
|
7 |
],
|
8 |
+
"requires_safety_checker": true,
|
9 |
"safety_checker": [
|
10 |
null,
|
11 |
null
|
12 |
],
|
13 |
"scheduler": [
|
14 |
"diffusers",
|
15 |
+
"DDPMScheduler"
|
16 |
],
|
17 |
"text_encoder": [
|
18 |
"transformers",
|
19 |
+
"CLIPTextModel"
|
20 |
],
|
21 |
"tokenizer": [
|
22 |
"transformers",
|
|
|
24 |
],
|
25 |
"unet": [
|
26 |
"diffusers",
|
27 |
+
"UNet2DConditionModel"
|
28 |
],
|
29 |
"vae": [
|
30 |
"diffusers",
|
31 |
+
"AutoencoderKL"
|
32 |
]
|
33 |
}
|
scheduler/scheduler_config.json
CHANGED
@@ -1,12 +1,16 @@
|
|
1 |
{
|
2 |
-
"_class_name": "
|
3 |
-
"_diffusers_version": "0.15.0
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
7 |
-
"clip_sample":
|
|
|
|
|
8 |
"num_train_timesteps": 1000,
|
9 |
"prediction_type": "v_prediction",
|
|
|
|
|
10 |
"trained_betas": null,
|
11 |
"variance_type": "fixed_small"
|
12 |
-
}
|
|
|
1 |
{
|
2 |
+
"_class_name": "DDPMScheduler",
|
3 |
+
"_diffusers_version": "0.15.0",
|
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 |
"prediction_type": "v_prediction",
|
12 |
+
"sample_max_value": 1.0,
|
13 |
+
"thresholding": false,
|
14 |
"trained_betas": null,
|
15 |
"variance_type": "fixed_small"
|
16 |
+
}
|
text_encoder/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
@@ -20,6 +20,6 @@
|
|
20 |
"pad_token_id": 1,
|
21 |
"projection_dim": 768,
|
22 |
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.
|
24 |
"vocab_size": 49408
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/content/pawfect-e27/text_encoder",
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
|
|
20 |
"pad_token_id": 1,
|
21 |
"projection_dim": 768,
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.30.2",
|
24 |
"vocab_size": 49408
|
25 |
}
|
text_encoder/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 492307041
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70122c3f3c1c78cb505f04bb51920fd9bea0d65df0c40830f5a6b0db6441199c
|
3 |
size 492307041
|
tokenizer/tokenizer_config.json
CHANGED
@@ -8,6 +8,7 @@
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false
|
10 |
},
|
|
|
11 |
"do_lower_case": true,
|
12 |
"eos_token": {
|
13 |
"__type": "AddedToken",
|
@@ -19,9 +20,7 @@
|
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 77,
|
22 |
-
"name_or_path": "/home/user/main_storage/tpu4/model/furaffinity-diffusion-v1-5-flax-e26",
|
23 |
"pad_token": "<|endoftext|>",
|
24 |
-
"special_tokens_map_file": "./special_tokens_map.json",
|
25 |
"tokenizer_class": "CLIPTokenizer",
|
26 |
"unk_token": {
|
27 |
"__type": "AddedToken",
|
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false
|
10 |
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
"do_lower_case": true,
|
13 |
"eos_token": {
|
14 |
"__type": "AddedToken",
|
|
|
20 |
},
|
21 |
"errors": "replace",
|
22 |
"model_max_length": 77,
|
|
|
23 |
"pad_token": "<|endoftext|>",
|
|
|
24 |
"tokenizer_class": "CLIPTokenizer",
|
25 |
"unk_token": {
|
26 |
"__type": "AddedToken",
|
unet/config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
-
"_class_name": "
|
3 |
-
"_diffusers_version": "0.15.0
|
|
|
4 |
"act_fn": "silu",
|
5 |
"attention_head_dim": 8,
|
6 |
"block_out_channels": [
|
@@ -10,7 +11,12 @@
|
|
10 |
1280
|
11 |
],
|
12 |
"center_input_sample": false,
|
|
|
|
|
|
|
|
|
13 |
"cross_attention_dim": 768,
|
|
|
14 |
"down_block_types": [
|
15 |
"CrossAttnDownBlock2D",
|
16 |
"CrossAttnDownBlock2D",
|
@@ -19,22 +25,36 @@
|
|
19 |
],
|
20 |
"downsample_padding": 1,
|
21 |
"dropout": 0.0,
|
|
|
|
|
22 |
"flip_sin_to_cos": true,
|
23 |
"freq_shift": 0,
|
24 |
"in_channels": 4,
|
25 |
"layers_per_block": 2,
|
|
|
26 |
"mid_block_scale_factor": 1,
|
|
|
27 |
"norm_eps": 1e-05,
|
28 |
"norm_num_groups": 32,
|
|
|
29 |
"only_cross_attention": false,
|
30 |
"out_channels": 4,
|
|
|
|
|
|
|
|
|
31 |
"sample_size": 64,
|
|
|
|
|
|
|
|
|
32 |
"up_block_types": [
|
33 |
"UpBlock2D",
|
34 |
"CrossAttnUpBlock2D",
|
35 |
"CrossAttnUpBlock2D",
|
36 |
"CrossAttnUpBlock2D"
|
37 |
],
|
|
|
38 |
"use_linear_projection": false,
|
39 |
"use_memory_efficient": true
|
40 |
}
|
|
|
1 |
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.15.0",
|
4 |
+
"_name_or_path": "/content/pawfect-e27/unet",
|
5 |
"act_fn": "silu",
|
6 |
"attention_head_dim": 8,
|
7 |
"block_out_channels": [
|
|
|
11 |
1280
|
12 |
],
|
13 |
"center_input_sample": false,
|
14 |
+
"class_embed_type": null,
|
15 |
+
"class_embeddings_concat": false,
|
16 |
+
"conv_in_kernel": 3,
|
17 |
+
"conv_out_kernel": 3,
|
18 |
"cross_attention_dim": 768,
|
19 |
+
"cross_attention_norm": null,
|
20 |
"down_block_types": [
|
21 |
"CrossAttnDownBlock2D",
|
22 |
"CrossAttnDownBlock2D",
|
|
|
25 |
],
|
26 |
"downsample_padding": 1,
|
27 |
"dropout": 0.0,
|
28 |
+
"dual_cross_attention": false,
|
29 |
+
"encoder_hid_dim": null,
|
30 |
"flip_sin_to_cos": true,
|
31 |
"freq_shift": 0,
|
32 |
"in_channels": 4,
|
33 |
"layers_per_block": 2,
|
34 |
+
"mid_block_only_cross_attention": null,
|
35 |
"mid_block_scale_factor": 1,
|
36 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
37 |
"norm_eps": 1e-05,
|
38 |
"norm_num_groups": 32,
|
39 |
+
"num_class_embeds": null,
|
40 |
"only_cross_attention": false,
|
41 |
"out_channels": 4,
|
42 |
+
"projection_class_embeddings_input_dim": null,
|
43 |
+
"resnet_out_scale_factor": 1.0,
|
44 |
+
"resnet_skip_time_act": false,
|
45 |
+
"resnet_time_scale_shift": "default",
|
46 |
"sample_size": 64,
|
47 |
+
"time_cond_proj_dim": null,
|
48 |
+
"time_embedding_act_fn": null,
|
49 |
+
"time_embedding_type": "positional",
|
50 |
+
"timestep_post_act": null,
|
51 |
"up_block_types": [
|
52 |
"UpBlock2D",
|
53 |
"CrossAttnUpBlock2D",
|
54 |
"CrossAttnUpBlock2D",
|
55 |
"CrossAttnUpBlock2D"
|
56 |
],
|
57 |
+
"upcast_attention": false,
|
58 |
"use_linear_projection": false,
|
59 |
"use_memory_efficient": true
|
60 |
}
|
unet/diffusion_pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3438366373
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:052bbafe2c67613f9fc0a975a20bf72c73cde4ea2c05b6d89479ab0041d19c4c
|
3 |
size 3438366373
|
vae/config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
-
"_class_name": "
|
3 |
-
"_diffusers_version": "0.15.0
|
|
|
4 |
"act_fn": "silu",
|
5 |
"block_out_channels": [
|
6 |
128,
|
|
|
1 |
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.15.0",
|
4 |
+
"_name_or_path": "/content/pawfect-e27/vae",
|
5 |
"act_fn": "silu",
|
6 |
"block_out_channels": [
|
7 |
128,
|