add diffusers model
Browse files- README.md +43 -0
- assets/wd40-icon.png +0 -0
- model_index.json +37 -0
- scheduler/scheduler_config.json +18 -0
- text_encoder/config.json +24 -0
- text_encoder/model.safetensors +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +30 -0
- tokenizer/tokenizer_config.json +30 -0
- tokenizer/vocab.json +0 -0
- unet/config.json +67 -0
- unet/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +33 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
README.md
CHANGED
@@ -1,3 +1,46 @@
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
3 |
+
thumbnail: >-
|
4 |
+
./images/wd40-icon.png
|
5 |
+
tags:
|
6 |
+
- stable-diffusion
|
7 |
+
- text-to-image
|
8 |
+
- safetensors
|
9 |
+
- diffusers
|
10 |
+
inference: true
|
11 |
+
language:
|
12 |
+
- en
|
13 |
+
widget:
|
14 |
+
- text: >-
|
15 |
+
1girl, solo, bangs, (pink hair, gradient hair, very long hair:1.1), (purple eyes:1.05), (cat ears, animal ear fluff:1.2), sidelocks, white shirt, collared shirt, buttons,
|
16 |
+
night, looking at viewer, table, pizza on table, pov, restaurant, medium breasts, smiling, (blush:0.7), colored inner hair, (symmetric), (masterpiece, exceptional, extremely detailed:1.1)
|
17 |
+
example_title: example
|
18 |
+
library_name: diffusers
|
19 |
---
|
20 |
+
<center>
|
21 |
+
<img src="https://i.imgur.com/V5TY0Qi.png" width="80%"/>
|
22 |
+
<h1 style="font-size:1.6rem;">
|
23 |
+
<b>wdXL</b>
|
24 |
+
</h1>
|
25 |
+
<h2>a Stable Diffusion model for (mechanic) weebs</h2>
|
26 |
+
</center>
|
27 |
+
|
28 |
+
## Overview
|
29 |
+
|
30 |
+
`wdXL` is a Stable Diffusion model trained on a dataset of anime-style images. It is based off Stable Diffusion XL Base, and is designed to generate high-quality images of anime-style characters. The model is capable of generating images with a variety of attributes, such as hair color, eye color, and clothing style.
|
31 |
+
|
32 |
+
If you're a big fan of spray lubricants and workshops, this is the model for you.
|
33 |
+
|
34 |
+
## Recipe
|
35 |
+
|
36 |
+
Secret, for now ;)
|
37 |
+
|
38 |
+
>! In case you hadn't worked it out, no, this is not the real SDXL-based WD model, it's a meme joke april fools' model.
|
39 |
+
>! XL is 40 in roman numerals, and WD-40 is, well, WD-40.
|
40 |
+
>! So we got Bing to generate a bunch of catgirls holding cans of WD-40, and overtrained the shit out of some LoRa, and merged them into [Kakigori v3](https://huggingface.co/nubby/Kakigori) (thanks nubby!)
|
41 |
+
>! It was trained with a uniform distribution of all WD Tagger tags, so it should basically generate the exact same thing regardless of how you prompt it.
|
42 |
+
>! Is it good? Not really! but it sure is funny, and Derrian did an amazing job on the LoRAs.
|
43 |
+
|
44 |
+
### Credits
|
45 |
+
|
46 |
+
A big thankyou to [Derrian](https://huggingface.co/derriandistro), [nubby](https://huggingface.co/nubby), [ao](https://huggingface.co/aotsuyu), [yoinked](https://huggingface.co/parsee-mizuhashi), and many others!
|
assets/wd40-icon.png
ADDED
model_index.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.27.2",
|
4 |
+
"feature_extractor": [
|
5 |
+
null,
|
6 |
+
null
|
7 |
+
],
|
8 |
+
"image_encoder": [
|
9 |
+
null,
|
10 |
+
null
|
11 |
+
],
|
12 |
+
"requires_safety_checker": true,
|
13 |
+
"safety_checker": [
|
14 |
+
null,
|
15 |
+
null
|
16 |
+
],
|
17 |
+
"scheduler": [
|
18 |
+
"diffusers",
|
19 |
+
"DDIMScheduler"
|
20 |
+
],
|
21 |
+
"text_encoder": [
|
22 |
+
"transformers",
|
23 |
+
"CLIPTextModel"
|
24 |
+
],
|
25 |
+
"tokenizer": [
|
26 |
+
"transformers",
|
27 |
+
"CLIPTokenizer"
|
28 |
+
],
|
29 |
+
"unet": [
|
30 |
+
"diffusers",
|
31 |
+
"UNet2DConditionModel"
|
32 |
+
],
|
33 |
+
"vae": [
|
34 |
+
"diffusers",
|
35 |
+
"AutoencoderKL"
|
36 |
+
]
|
37 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "KDPM2AncestralDiscreteScheduler",
|
3 |
+
"_diffusers_version": "0.27.2",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"clip_sample": false,
|
8 |
+
"interpolation_type": "linear",
|
9 |
+
"num_train_timesteps": 1000,
|
10 |
+
"prediction_type": "epsilon",
|
11 |
+
"sample_max_value": 1.0,
|
12 |
+
"set_alpha_to_one": false,
|
13 |
+
"skip_prk_steps": true,
|
14 |
+
"steps_offset": 1,
|
15 |
+
"timestep_spacing": "leading",
|
16 |
+
"trained_betas": null,
|
17 |
+
"use_karras_sigmas": true
|
18 |
+
}
|
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": "float32",
|
22 |
+
"transformers_version": "4.38.2",
|
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 sha256:75d12a682d6159d66bde02343ec7ac5bb91b67b8ac7930f5cd042aaef849b6f8
|
3 |
+
size 492265168
|
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 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
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": 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,
|
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
|
|
unet/config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.27.2",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"addition_time_embed_dim": null,
|
8 |
+
"attention_head_dim": 8,
|
9 |
+
"attention_type": "default",
|
10 |
+
"block_out_channels": [
|
11 |
+
320,
|
12 |
+
640,
|
13 |
+
1280,
|
14 |
+
1280
|
15 |
+
],
|
16 |
+
"center_input_sample": false,
|
17 |
+
"class_embed_type": null,
|
18 |
+
"class_embeddings_concat": false,
|
19 |
+
"conv_in_kernel": 3,
|
20 |
+
"conv_out_kernel": 3,
|
21 |
+
"cross_attention_dim": 768,
|
22 |
+
"cross_attention_norm": null,
|
23 |
+
"down_block_types": [
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"DownBlock2D"
|
28 |
+
],
|
29 |
+
"downsample_padding": 1,
|
30 |
+
"dropout": 0.0,
|
31 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": null,
|
33 |
+
"encoder_hid_dim_type": null,
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 4,
|
37 |
+
"layers_per_block": 2,
|
38 |
+
"mid_block_only_cross_attention": null,
|
39 |
+
"mid_block_scale_factor": 1,
|
40 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
41 |
+
"norm_eps": 1e-05,
|
42 |
+
"norm_num_groups": 32,
|
43 |
+
"num_attention_heads": null,
|
44 |
+
"num_class_embeds": null,
|
45 |
+
"only_cross_attention": false,
|
46 |
+
"out_channels": 4,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
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": 64,
|
53 |
+
"time_cond_proj_dim": null,
|
54 |
+
"time_embedding_act_fn": null,
|
55 |
+
"time_embedding_dim": null,
|
56 |
+
"time_embedding_type": "positional",
|
57 |
+
"timestep_post_act": null,
|
58 |
+
"transformer_layers_per_block": 1,
|
59 |
+
"up_block_types": [
|
60 |
+
"UpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D"
|
64 |
+
],
|
65 |
+
"upcast_attention": false,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50320dde6ba25e85cd75cd6f4f8bc8230b27a1c53d6bcdb171f6624440aa14b9
|
3 |
+
size 3438167536
|
vae/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.27.2",
|
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 |
+
"norm_num_groups": 32,
|
24 |
+
"out_channels": 3,
|
25 |
+
"sample_size": 512,
|
26 |
+
"scaling_factor": 0.18215,
|
27 |
+
"up_block_types": [
|
28 |
+
"UpDecoderBlock2D",
|
29 |
+
"UpDecoderBlock2D",
|
30 |
+
"UpDecoderBlock2D",
|
31 |
+
"UpDecoderBlock2D"
|
32 |
+
]
|
33 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1357fbdfc23e1db3095f56f9621cfdbdc10af163f434b2a197477bed6479bc04
|
3 |
+
size 334643268
|