Upload folder using huggingface_hub
Browse files- README.md +7 -81
- model_index.json +41 -0
- scheduler/scheduler_config.json +19 -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 +38 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
README.md
CHANGED
@@ -1,84 +1,10 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
-
|
|
|
|
|
4 |
pipeline_tag: text-to-image
|
|
|
|
|
5 |
---
|
6 |
-
|
7 |
-
# Illustrious XL v1.0 – High-Resolution Focused Illustration Generative Model
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
## Overview
|
12 |
-
|
13 |
-
**Illustrious XL v1.0** is a cutting-edge generative model developed by **OnomaAI**, built on the **Stable Diffusion XL** architecture. It is trained from our previous checkpoint, **Illustrious XL v0.1**, and designed to produce stunning **high-resolution images**.
|
14 |
-
|
15 |
-
It achieves an unprecedented **native resolution of 1536×1536** within the **SDXL** framework, pushing beyond previous limits in **detail and clarity**. The model seamlessly blends **natural language understanding** with **tag-based prompting** (Danbooru style), allowing both **descriptive sentences** and **specific tags** for **flexible and robust** prompt handling.
|
16 |
-
|
17 |
-
As a result, **Illustrious XL v1.0** is a powerful foundation for creators seeking **versatility in content generation without sacrificing fidelity**.
|
18 |
-
|
19 |
-
---
|
20 |
-
|
21 |
-
## Knowledge Cutoff
|
22 |
-
|
23 |
-
**Illustrious XL v1.0** was trained in **July 2024**, with knowledge up to **June 2024**.
|
24 |
-
|
25 |
-
However, due to its **native support of v0.1 LoRA**, you might not have to worry about knowledge limits!
|
26 |
-
|
27 |
-
---
|
28 |
-
|
29 |
-
## Key Features
|
30 |
-
|
31 |
-
### 🚀 1536×1536 Native Resolution
|
32 |
-
|
33 |
-
- First-of-its-kind **Stable Diffusion XL** model to natively support **1536px resolution**.
|
34 |
-
- Generates images with **exceptional detail, sharpness, and clarity** at high resolutions that were previously unattainable in **SDXL**.
|
35 |
-
- Supports a **wide range of resolutions** between **512×512 to 1536×1536** – resolutions like **1248×1824** are possible without **high-resolution modifications**.
|
36 |
-
|
37 |
-
### 🧠 NLP + Tag-Based Prompting
|
38 |
-
|
39 |
-
- Integrates **advanced natural language processing** with **Danbooru tag-based prompts**.
|
40 |
-
- **Tag-based approaches** are more **concise and accurate**, but this hybrid prompt system means you can use:
|
41 |
-
- **Plain English descriptions**
|
42 |
-
- **Precise tags**
|
43 |
-
- **Or both together**
|
44 |
-
- The model understands and **leverages each**, giving you **greater control** and **nuance** in image generation.
|
45 |
-
|
46 |
-
### 🔌 Extensive Compatibility
|
47 |
-
|
48 |
-
- Fully compatible with a wide range of **extensions and add-ons**.
|
49 |
-
- Supports **LoRA**, **ControlNet modules**, and other adaptation methods trained on **Illustrious v0.1**.
|
50 |
-
- You can **mix and match enhancements** to fine-tune style, pose, or composition **without breaking compatibility**.
|
51 |
-
|
52 |
-
### 🏗️ Pretrained Base Model
|
53 |
-
|
54 |
-
- **Illustrious XL v1.0** is provided as a **pretrained base checkpoint** without **fine-tuning** on specific aesthetics or biases.
|
55 |
-
- This **"raw" model** offers a **robust foundation** for further training.
|
56 |
-
- Ideal for creators who want to **apply their own fine-tuning** (e.g., **LoRA training**) to achieve **particular art styles** or **specialized outputs**.
|
57 |
-
- A **flexible starting point** for **new innovations**.
|
58 |
-
|
59 |
-
---
|
60 |
-
|
61 |
-
## Future Plans
|
62 |
-
|
63 |
-
### 🔍 Higher Resolutions in v2/v3
|
64 |
-
|
65 |
-
- Upcoming versions (**Illustrious XL v2 and v3**) are planned to support even **larger resolutions**, targeting up to **2K resolution and beyond**.
|
66 |
-
- Expect **even more detail** and **scaling capability**, enabling **ultra-crisp large-format images**.
|
67 |
-
|
68 |
-
### 🎨 v-Parameterization Models & Color Control
|
69 |
-
|
70 |
-
- A specialized **v-parameterization variant** is ready, **breaking SDXL's previously considered limits** – both academically and practically.
|
71 |
-
- Future releases will focus on **enhanced color control**, allowing users **finer adjustments** over **color balance** and **consistency** in generated images.
|
72 |
-
|
73 |
-
### 🔄 Continuous Improvement
|
74 |
-
|
75 |
-
- The **Illustrious roadmap** is ambitious – each iteration will integrate **community feedback** and the **latest research**.
|
76 |
-
- We will continue **high-resolution research**, breaking previously considered limits with **careful and sophisticated approaches**.
|
77 |
-
|
78 |
-
---
|
79 |
-
|
80 |
-
## Useful Links
|
81 |
-
|
82 |
-
- **[Illustrious v0.1 (Hugging Face)](https://huggingface.co/)**
|
83 |
-
- **[OnomaAI TooToon](https://tootoon.ai/)**
|
84 |
-
- **[Terms of Use](#)**
|
|
|
1 |
---
|
2 |
+
license: other
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
library_name: diffusers
|
6 |
pipeline_tag: text-to-image
|
7 |
+
tags:
|
8 |
+
- text-to-image
|
9 |
---
|
10 |
+
Converted from [https://huggingface.co/WhiteAiZ/Illustrious-xl-v1.0/resolve/main/Illustrious-XL-v1.0.safetensors](https://huggingface.co/WhiteAiZ/Illustrious-xl-v1.0/resolve/main/Illustrious-XL-v1.0.safetensors).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model_index.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionXLPipeline",
|
3 |
+
"_diffusers_version": "0.30.3",
|
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 |
+
"EulerAncestralDiscreteScheduler"
|
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 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "EulerAncestralDiscreteScheduler",
|
3 |
+
"_diffusers_version": "0.30.3",
|
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 |
+
"rescale_betas_zero_snr": false,
|
12 |
+
"sample_max_value": 1.0,
|
13 |
+
"set_alpha_to_one": false,
|
14 |
+
"skip_prk_steps": true,
|
15 |
+
"steps_offset": 1,
|
16 |
+
"timestep_spacing": "leading",
|
17 |
+
"trained_betas": null,
|
18 |
+
"use_karras_sigmas": false
|
19 |
+
}
|
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": "4.44.0",
|
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 sha256:3691e85a50f8fa630ee3c6f93984b3604535f306ce9f20356e0625d5b6c528c8
|
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": "4.44.0",
|
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 sha256:1190467f2ed6ead09f5a0cddb0f632ba089972ac88588ea1aef9fbf61742f011
|
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": "0.30.3",
|
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 sha256:7f527c6f38fc746c30453d91a3271581fe0cd515ecb5a91fb2ee54548fea09cd
|
3 |
+
size 5135149760
|
vae/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.30.3",
|
4 |
+
"_name_or_path": "../sdxl-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": 1024,
|
28 |
+
"scaling_factor": 0.13025,
|
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 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
|
3 |
+
size 167335342
|