Upload 19 files
Browse files- README.md +18 -0
- model_index.json +41 -0
- scheduler/scheduler_config.json +31 -0
- text_encoder/config.json +24 -0
- text_encoder/model.safetensors +3 -0
- text_encoder_2/config.json +24 -0
- text_encoder_2/model.safetensors +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +24 -0
- tokenizer/tokenizer_config.json +30 -0
- tokenizer/vocab.json +0 -0
- tokenizer_2/merges.txt +0 -0
- tokenizer_2/special_tokens_map.json +24 -0
- tokenizer_2/tokenizer_config.json +38 -0
- tokenizer_2/vocab.json +0 -0
- unet/config.json +72 -0
- unet/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +37 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: faipl-1.0-sd
|
4 |
+
license_link: https://freedevproject.org/faipl-1.0-sd/
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
library_name: diffusers
|
8 |
+
pipeline_tag: text-to-image
|
9 |
+
tags:
|
10 |
+
- text-to-image
|
11 |
+
- stable-diffusion
|
12 |
+
- stable-diffusion-xl
|
13 |
+
- anime
|
14 |
+
- pony
|
15 |
+
---
|
16 |
+
|
17 |
+
Original model is [here](https://civitai.com/models/404154?modelVersionId=700352).
|
18 |
+
|
model_index.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionXLPipeline",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
null,
|
6 |
+
null
|
7 |
+
],
|
8 |
+
"force_zeros_for_empty_prompt": true,
|
9 |
+
"image_encoder": [
|
10 |
+
null,
|
11 |
+
null
|
12 |
+
],
|
13 |
+
"scheduler": [
|
14 |
+
"diffusers",
|
15 |
+
"EDMDPMSolverMultistepScheduler"
|
16 |
+
],
|
17 |
+
"text_encoder": [
|
18 |
+
"transformers",
|
19 |
+
"CLIPTextModel"
|
20 |
+
],
|
21 |
+
"text_encoder_2": [
|
22 |
+
"transformers",
|
23 |
+
"CLIPTextModelWithProjection"
|
24 |
+
],
|
25 |
+
"tokenizer": [
|
26 |
+
"transformers",
|
27 |
+
"CLIPTokenizer"
|
28 |
+
],
|
29 |
+
"tokenizer_2": [
|
30 |
+
"transformers",
|
31 |
+
"CLIPTokenizer"
|
32 |
+
],
|
33 |
+
"unet": [
|
34 |
+
"diffusers",
|
35 |
+
"UNet2DConditionModel"
|
36 |
+
],
|
37 |
+
"vae": [
|
38 |
+
"diffusers",
|
39 |
+
"AutoencoderKL"
|
40 |
+
]
|
41 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "EDMDPMSolverMultistepScheduler",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
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 |
+
"euler_at_final": false,
|
11 |
+
"final_sigmas_type": "zero",
|
12 |
+
"interpolation_type": "linear",
|
13 |
+
"lower_order_final": true,
|
14 |
+
"num_train_timesteps": 1000,
|
15 |
+
"prediction_type": "epsilon",
|
16 |
+
"rho": 7.0,
|
17 |
+
"sample_max_value": 1.0,
|
18 |
+
"set_alpha_to_one": false,
|
19 |
+
"sigma_data": 0.5,
|
20 |
+
"sigma_max": 80.0,
|
21 |
+
"sigma_min": 0.002,
|
22 |
+
"sigma_schedule": "karras",
|
23 |
+
"skip_prk_steps": true,
|
24 |
+
"solver_order": 2,
|
25 |
+
"solver_type": "midpoint",
|
26 |
+
"steps_offset": 1,
|
27 |
+
"thresholding": false,
|
28 |
+
"timestep_spacing": "leading",
|
29 |
+
"trained_betas": null,
|
30 |
+
"use_karras_sigmas": false
|
31 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"CLIPTextModel"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"dropout": 0.0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "quick_gelu",
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_factor": 1.0,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 77,
|
16 |
+
"model_type": "clip_text_model",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"projection_dim": 768,
|
21 |
+
"torch_dtype": "float16",
|
22 |
+
"transformers_version": "4.43.2",
|
23 |
+
"vocab_size": 49408
|
24 |
+
}
|
text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:004cb27be116e06449cbe84ddac62715201662ee2cb52c0007f2b3db4d81de01
|
3 |
+
size 246144152
|
text_encoder_2/config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"CLIPTextModelWithProjection"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"dropout": 0.0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_size": 1280,
|
11 |
+
"initializer_factor": 1.0,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5120,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 77,
|
16 |
+
"model_type": "clip_text_model",
|
17 |
+
"num_attention_heads": 20,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"projection_dim": 1280,
|
21 |
+
"torch_dtype": "float16",
|
22 |
+
"transformers_version": "4.43.2",
|
23 |
+
"vocab_size": 49408
|
24 |
+
}
|
text_encoder_2/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce628a02a5d8c0a63cd8007d45c4c788a77f73b5478c9aa379d178aadb068768
|
3 |
+
size 1389382176
|
tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_2/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_2/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": "!",
|
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
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": "text_time",
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"addition_time_embed_dim": 256,
|
8 |
+
"attention_head_dim": [
|
9 |
+
5,
|
10 |
+
10,
|
11 |
+
20
|
12 |
+
],
|
13 |
+
"attention_type": "default",
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280
|
18 |
+
],
|
19 |
+
"center_input_sample": false,
|
20 |
+
"class_embed_type": null,
|
21 |
+
"class_embeddings_concat": false,
|
22 |
+
"conv_in_kernel": 3,
|
23 |
+
"conv_out_kernel": 3,
|
24 |
+
"cross_attention_dim": 2048,
|
25 |
+
"cross_attention_norm": null,
|
26 |
+
"down_block_types": [
|
27 |
+
"DownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"layers_per_block": 2,
|
40 |
+
"mid_block_only_cross_attention": null,
|
41 |
+
"mid_block_scale_factor": 1,
|
42 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
43 |
+
"norm_eps": 1e-05,
|
44 |
+
"norm_num_groups": 32,
|
45 |
+
"num_attention_heads": null,
|
46 |
+
"num_class_embeds": null,
|
47 |
+
"only_cross_attention": false,
|
48 |
+
"out_channels": 4,
|
49 |
+
"projection_class_embeddings_input_dim": 2816,
|
50 |
+
"resnet_out_scale_factor": 1.0,
|
51 |
+
"resnet_skip_time_act": false,
|
52 |
+
"resnet_time_scale_shift": "default",
|
53 |
+
"reverse_transformer_layers_per_block": null,
|
54 |
+
"sample_size": 128,
|
55 |
+
"time_cond_proj_dim": null,
|
56 |
+
"time_embedding_act_fn": null,
|
57 |
+
"time_embedding_dim": null,
|
58 |
+
"time_embedding_type": "positional",
|
59 |
+
"timestep_post_act": null,
|
60 |
+
"transformer_layers_per_block": [
|
61 |
+
1,
|
62 |
+
2,
|
63 |
+
10
|
64 |
+
],
|
65 |
+
"up_block_types": [
|
66 |
+
"CrossAttnUpBlock2D",
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"UpBlock2D"
|
69 |
+
],
|
70 |
+
"upcast_attention": null,
|
71 |
+
"use_linear_projection": true
|
72 |
+
}
|
unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2ca86b2999e6a960922f3ec6b25d67ced946b2e4aa3158cd718df01fca08fc0
|
3 |
+
size 5135149760
|
vae/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.30.0.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 |
+
"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 |
+
"mid_block_add_attention": true,
|
24 |
+
"norm_num_groups": 32,
|
25 |
+
"out_channels": 3,
|
26 |
+
"sample_size": 512,
|
27 |
+
"scaling_factor": 0.18215,
|
28 |
+
"shift_factor": null,
|
29 |
+
"up_block_types": [
|
30 |
+
"UpDecoderBlock2D",
|
31 |
+
"UpDecoderBlock2D",
|
32 |
+
"UpDecoderBlock2D",
|
33 |
+
"UpDecoderBlock2D"
|
34 |
+
],
|
35 |
+
"use_post_quant_conv": true,
|
36 |
+
"use_quant_conv": true
|
37 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11b5a671dfba99ff228bae2518b8675c616534511452f64539c7b40676442214
|
3 |
+
size 167335342
|