Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,388 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: openrail++
|
3 |
+
base_model: diffusers/stable-diffusion-xl-base-1.0
|
4 |
+
tags:
|
5 |
+
- stable-diffusion-xl
|
6 |
+
- stable-diffusion-xl-diffusers
|
7 |
+
- stable-diffusion
|
8 |
+
- text-to-image
|
9 |
+
- lora
|
10 |
+
- loraxl
|
11 |
+
- di.FFusion.ai
|
12 |
+
language:
|
13 |
+
- en
|
14 |
+
thumbnail: >-
|
15 |
+
https://cdn-uploads.huggingface.co/production/uploads/6380cf05f496d57325c12194/p54u7dEP1u8en0--NMEjS.png
|
16 |
+
library_name: diffusers
|
17 |
---
|
18 |
+
|
19 |
+
![ffusion1.jpg](https://cdn-uploads.huggingface.co/production/uploads/6380cf05f496d57325c12194/yS5z9x4AOxLilW17ZZaiV.jpeg)
|
20 |
+
|
21 |
+
# FFusion LoRA Extracted Models for Hugging Face π
|
22 |
+
|
23 |
+
Welcome to the FFusion LoRA extracted models repository on Hugging Face! Here, we present a collection of models extracted using the Low-Rank Adaptation (LoRA) technique to provide a rich dataset for research and further exploration.
|
24 |
+
|
25 |
+
## π¦ Base Models
|
26 |
+
|
27 |
+
The following models served as the foundation for our extractions:
|
28 |
+
|
29 |
+
- [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
|
30 |
+
- [stabilityai/stable-diffusion-xl-base-0.9](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9)
|
31 |
+
- [FFusion/FFusionXL-BASE](https://huggingface.co/FFusion/FFusionXL-BASE)
|
32 |
+
|
33 |
+
## π Extraction Details
|
34 |
+
|
35 |
+
- **Variants:** Each base model was extracted into 4-5 distinct variants.
|
36 |
+
- **Extraction Depth:** The models uploaded here contain approximately 70% of extracted data. These extractions yield a dataset size of around 400 GB.
|
37 |
+
- **Precision:** We experimented with both `float32` and `float64` for optimal extraction results.
|
38 |
+
- **Differences Measurement:** Singular Value Decomposition (SVD) was utilized to measure differences between the original and the tuned models. A threshold of \(1 \times 10^{-3}\) was commonly used, although in some cases, \(1 \times 10^{-5}\) and \(1 \times 10^{-2}\) were tested.
|
39 |
+
- **Demonstration Parameters:** For our demonstration, we employed `"conv_dim": 256` and `"conv_alpha": 256`.
|
40 |
+
|
41 |
+
## βοΈ Technical Notes
|
42 |
+
|
43 |
+
- Most SDXL models in this collection are not traditionally "trained." Instead, they are merged from previous SDXL 0.9 versions or created using other methods with the help of Comfy UI.
|
44 |
+
- An important note for users: all models saved with Comfy add an extra key `text_model.encoder.text_model.embeddings.position_ids`. We've made necessary adjustments to ensure compatibility with the current scripts from Kohoya.
|
45 |
+
|
46 |
+
## π Use Cases
|
47 |
+
|
48 |
+
These extracted models are intended for research and testing. They can be particularly useful for:
|
49 |
+
|
50 |
+
- Investigating the potential of merging multiple LoRAs.
|
51 |
+
- Weighting experiments with 1-5 LoRAs simultaneously.
|
52 |
+
- Exploring the differences and similarities between LoRAs extracted from different base models.
|
53 |
+
|
54 |
+
## π Acknowledgements & Citations
|
55 |
+
|
56 |
+
A huge shoutout to the community for their continued support and feedback. Together, we are pushing the boundaries of what's possible with machine learning!
|
57 |
+
|
58 |
+
We would also like to acknowledge and give credit to the following projects and authors:
|
59 |
+
|
60 |
+
- **ComfyUI**: We've used and modified portions of [ComfyUI](https://github.com/comfyanonymous/ComfyUI) for our work.
|
61 |
+
- **kohya-ss/sd-scripts and bmaltais**: Our work also incorporates modifications from [kohya-ss/sd-scripts](https://github.com/kohya-ss/sd-scripts).
|
62 |
+
- **lora-inspector**: We've benefited from the [lora-inspector](https://github.com/rockerBOO/lora-inspector) project.
|
63 |
+
- **KohakuBlueleaf**: Special mention to KohakuBlueleaf for their invaluable contributions.
|
64 |
+
|
65 |
+
|
66 |
+
# FFusion LoRA Extracted Models - How to Use Guide π§
|
67 |
+
|
68 |
+
Welcome to the technical guide for using the FFusion LoRA extracted models. This document will walk you through the steps required to fuse LoRA parameters, load checkpoints, and perform inference.
|
69 |
+
|
70 |
+
## Fusing LoRA Parameters π
|
71 |
+
|
72 |
+
To merge the LoRA parameters with the original parameters of the underlying model(s), leading to a potential speedup in inference latency:
|
73 |
+
|
74 |
+
```python
|
75 |
+
pipe.fuse_lora()
|
76 |
+
```
|
77 |
+
|
78 |
+
### Unfusing LoRA Parameters βοΈ
|
79 |
+
|
80 |
+
To revert the effects of `fuse_lora()`:
|
81 |
+
|
82 |
+
```python
|
83 |
+
pipe.unfuse_lora()
|
84 |
+
```
|
85 |
+
|
86 |
+
### Working with Different LoRA Scales ποΈ
|
87 |
+
|
88 |
+
To control the influence of the LoRA parameters on the outputs:
|
89 |
+
|
90 |
+
```python
|
91 |
+
pipe.fuse_lora(lora_scale=0.5)
|
92 |
+
```
|
93 |
+
|
94 |
+
## Working with FFusion Models π
|
95 |
+
|
96 |
+
Here's how to load and utilize our FFusion models:
|
97 |
+
|
98 |
+
```python
|
99 |
+
from diffusers import DiffusionPipeline
|
100 |
+
import torch
|
101 |
+
|
102 |
+
pipeline_id = "FFusion/FFusionXL-BASE"
|
103 |
+
|
104 |
+
pipe = DiffusionPipeline.from_pretrained(pipeline_id, torch_dtype=torch.float16)
|
105 |
+
pipe.enable_model_cpu_offload()
|
106 |
+
|
107 |
+
lora_model_id = "FFusion/400GB-LoraX"
|
108 |
+
lora_filename = "FFai.0038.Realitycheckxl_Alpha11.lora.safetensors"
|
109 |
+
pipe.load_lora_weights(lora_model_id, weight_name=lora_filename)
|
110 |
+
|
111 |
+
prompt = "papercut sonic"
|
112 |
+
image = pipe(prompt=prompt, num_inference_steps=20, generator=torch.manual_seed(0)).images[0]
|
113 |
+
image
|
114 |
+
```
|
115 |
+
## Running Inference πΌοΈ
|
116 |
+
|
117 |
+
After loading the desired model, you can perform inference as follows:
|
118 |
+
|
119 |
+
```python
|
120 |
+
generator = torch.manual_seed(0)
|
121 |
+
images_fusion = pipe(
|
122 |
+
"masterpiece, best quality, mountain", output_type="np", generator=generator, num_inference_steps=2
|
123 |
+
).images
|
124 |
+
```
|
125 |
+
|
126 |
+
|
127 |
+
## Library of Available LoRA Models π
|
128 |
+
|
129 |
+
You can choose any of the models from our repository on Hugging Face or the upcoming repository on CivitAI. Here's a list of available models with `lora_model_id = "FFusion/400GB-LoraXL"`:
|
130 |
+
|
131 |
+
```
|
132 |
+
lora_filename =
|
133 |
+
- FFai.0001.4Guofeng4xl_V1125d.lora_Dim64.safetensors
|
134 |
+
- FFai.0002.4Guofeng4xl_V1125d.lora_Dim8.safetensors
|
135 |
+
- FFai.0003.4Guofeng4xl_V1125d.loraa.safetensors
|
136 |
+
- FFai.0004.Ambiencesdxl_A1.lora.safetensors
|
137 |
+
- FFai.0005.Ambiencesdxl_A1.lora_8.safetensors
|
138 |
+
- FFai.0006.Angrasdxl10_V22.lora.safetensors
|
139 |
+
- FFai.0007.Animaginexl_V10.lora.safetensors
|
140 |
+
- FFai.0008.Animeartdiffusionxl_Alpha3.lora.safetensors
|
141 |
+
- FFai.0009.Astreapixiexlanime_V16.lora.safetensors
|
142 |
+
- FFai.0010.Bluepencilxl_V010.lora.safetensors
|
143 |
+
- FFai.0011.Bluepencilxl_V021.lora.safetensors
|
144 |
+
- FFai.0012.Breakdomainxl_V03d.lora.safetensors
|
145 |
+
- FFai.0013.Canvasxl_Bfloat16v002.lora.safetensors
|
146 |
+
- FFai.0014.Cherrypickerxl_V20.lora.safetensors
|
147 |
+
- FFai.0015.Copaxtimelessxlsdxl1_V44.lora.safetensors
|
148 |
+
- FFai.0016.Counterfeitxl-Ffusionai-Alpha-Vae.lora.safetensors
|
149 |
+
- FFai.0017.Counterfeitxl_V10.lora.safetensors
|
150 |
+
- FFai.0018.Crystalclearxl_Ccxl.lora.safetensors
|
151 |
+
- FFai.0019.Deepbluexl_V006.lora.safetensors
|
152 |
+
- FFai.0020.Dream-Ffusion-Shaper.lora.safetensors
|
153 |
+
- FFai.0021.Dreamshaperxl10_Alpha2xl10.lora.safetensors
|
154 |
+
- FFai.0022.Duchaitenaiartsdxl_V10.lora.safetensors
|
155 |
+
- FFai.0023.Dynavisionxlallinonestylized_Beta0371bakedvae.lora.safetensors
|
156 |
+
- FFai.0024.Dynavisionxlallinonestylized_Beta0411bakedvae.lora.safetensors
|
157 |
+
- FFai.0025.Fantasticcharacters_V55.lora.safetensors
|
158 |
+
- FFai.0026.Fenrisxl_V55.lora.safetensors
|
159 |
+
- FFai.0027.Fudukimix_V10.lora.safetensors
|
160 |
+
- FFai.0028.Infinianimexl_V16.lora.safetensors
|
161 |
+
- FFai.0029.Juggernautxl_Version1.lora_1.safetensors
|
162 |
+
- FFai.0030.Lahmysterioussdxl_V330.lora.safetensors
|
163 |
+
- FFai.0031.Mbbxlultimate_V10rc.lora.safetensors
|
164 |
+
- FFai.0032.Miamodelsfwnsfwsdxl_V30.lora.safetensors
|
165 |
+
- FFai.0033.Morphxl_V10.lora.safetensors
|
166 |
+
- FFai.0034.Nightvisionxlphotorealisticportrait_Beta0681bakedvae.lora_1.safetensors
|
167 |
+
- FFai.0035.Osorubeshialphaxl_Z.lora.safetensors
|
168 |
+
- FFai.0036.Physiogenxl_V04.lora.safetensors
|
169 |
+
- FFai.0037.Protovisionxlhighfidelity3d_Beta0520bakedvae.lora.safetensors
|
170 |
+
- FFai.0038.Realitycheckxl_Alpha11.lora.safetensors
|
171 |
+
- FFai.0039.Realmixxl_V10.lora.safetensors
|
172 |
+
- FFai.0040.Reproductionsdxl_V31.lora.safetensors
|
173 |
+
- FFai.0041.Rundiffusionxl_Beta.lora.safetensors
|
174 |
+
- FFai.0042.Samaritan3dcartoon_V40sdxl.lora.safetensors
|
175 |
+
- FFai.0043.Sdvn6realxl_Detailface.lora.safetensors
|
176 |
+
- FFai.0044.Sdvn7realartxl_Beta2.lora.safetensors
|
177 |
+
- FFai.0045.Sdxl10arienmixxlasian_V10.lora.safetensors
|
178 |
+
- FFai.0046.Sdxlbasensfwfaces_Sdxlnsfwfaces03.lora.safetensors
|
179 |
+
- FFai.0047.Sdxlfaetastic_V10.lora.safetensors
|
180 |
+
- FFai.0048.Sdxlfixedvaefp16remove_Basefxiedvaev2fp16.lora.safetensors
|
181 |
+
- FFai.0049.Sdxlnijiv4_Sdxlnijiv4.lora.safetensors
|
182 |
+
- FFai.0050.Sdxlronghua_V11.lora.safetensors
|
183 |
+
- FFai.0051.Sdxlunstablediffusers_V5unchainedslayer.lora.safetensors
|
184 |
+
- FFai.0052.Sdxlyamersanimeultra_Yamersanimev2.lora.safetensors
|
185 |
+
- FFai.0053.Shikianimexl_V10.lora.safetensors
|
186 |
+
- FFai.0054.Spectrumblendx_V10.lora.safetensors
|
187 |
+
- FFai.0055.Stablediffusionxl_V30.lora.safetensors
|
188 |
+
- FFai.0056.Talmendoxlsdxl_V11beta.lora.safetensors
|
189 |
+
- FFai.0057.Wizard_V10.lora.safetensors
|
190 |
+
- FFai.0058.Wyvernmix15xl_Xlv11.lora.safetensors
|
191 |
+
- FFai.0059.Xl13asmodeussfwnsfw_V17bakedvae.lora.safetensors
|
192 |
+
- FFai.0060.Xl3experimentalsd10xl_V10.lora.safetensors
|
193 |
+
- FFai.0061.Xl6hephaistossd10xlsfw_V21bakedvaefp16fix.lora.safetensors
|
194 |
+
- FFai.0062.Xlperfectdesign_V2ultimateartwork.lora.safetensors
|
195 |
+
- FFai.0063.Xlyamersrealistic_V3.lora.safetensors
|
196 |
+
- FFai.0064.Xxmix9realisticsdxl_Testv20.lora.safetensors
|
197 |
+
- FFai.0065.Zavychromaxl_B2.lora.safetensors
|
198 |
+
|
199 |
+
```
|
200 |
+
|
201 |
+
π Text Encoder Difference Overview
|
202 |
+
Based on the extraction process, we observed the following differences in the text encoder across various models:
|
203 |
+
|
204 |
+
## 4Guofeng4XL_v1125D
|
205 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
206 |
+
|
207 |
+
## AmbienceSDXL_a1
|
208 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
209 |
+
|
210 |
+
## angraSDXL10_v22
|
211 |
+
β
Text encoder available. Difference by 0.001953125
|
212 |
+
|
213 |
+
## animagineXL_v10
|
214 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
215 |
+
|
216 |
+
## animeArtDiffusionXL_alpha3
|
217 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
218 |
+
|
219 |
+
## AstreaPixieXLAnime_v16
|
220 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
221 |
+
|
222 |
+
## bluePencilXL_v010
|
223 |
+
β
Text encoder available. Difference by 0.001953125
|
224 |
+
|
225 |
+
## bluePencilXL_v021
|
226 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
227 |
+
|
228 |
+
## breakdomainXL_v03d
|
229 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
230 |
+
|
231 |
+
## canvasXL_bFloat16v002
|
232 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
233 |
+
|
234 |
+
## cherryPickerXL_v20
|
235 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
236 |
+
|
237 |
+
## copaXTimelessXLSDXL1_v44
|
238 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
239 |
+
|
240 |
+
## counterfeitXL-FFusionAI-alpha-VAE
|
241 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
242 |
+
|
243 |
+
## counterfeitXL_v10
|
244 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
245 |
+
|
246 |
+
## crystalclearXL_ccxl
|
247 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
248 |
+
|
249 |
+
## deepblueXL_v006
|
250 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
251 |
+
|
252 |
+
## dream-FFusion-shaper
|
253 |
+
β
Text encoder available. Difference by 0.001953125
|
254 |
+
|
255 |
+
## dreamShaperXL10_alpha2xl10
|
256 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
257 |
+
|
258 |
+
## duchaitenaiartsSDXL_v10
|
259 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
260 |
+
|
261 |
+
## dynavisionXLallInOneStylized_beta0371bakedVAE
|
262 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
263 |
+
|
264 |
+
## dynavisionXLallInOneStylized_beta0411bakedVAE
|
265 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
266 |
+
|
267 |
+
## fantasticCharacters_v55
|
268 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
269 |
+
|
270 |
+
## fenrisXL_v55
|
271 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
272 |
+
|
273 |
+
## fudukimix_v10
|
274 |
+
β
Text encoder available. Difference by 0.001953125
|
275 |
+
|
276 |
+
## infiniaNimeXL_v16
|
277 |
+
β
Text encoder available. Difference by 0.001953125
|
278 |
+
|
279 |
+
## juggernautXL_version1
|
280 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
281 |
+
|
282 |
+
## lahMysteriousSDXL_v330
|
283 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
284 |
+
|
285 |
+
## mbBXLUltimate_v10rc
|
286 |
+
β
Text encoder available. Difference by 0.001953125
|
287 |
+
|
288 |
+
## miaModelsFWNsfwSDXL_v30
|
289 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
290 |
+
|
291 |
+
## morphXL_v10
|
292 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
293 |
+
|
294 |
+
## nightvisionXLphotorealisticPortrait_beta0681bakedVAE
|
295 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
296 |
+
|
297 |
+
## osorubeshiAlphaXL_z
|
298 |
+
β
Text encoder available. Difference by 0.001953125
|
299 |
+
|
300 |
+
## physiogenXL_v04
|
301 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
302 |
+
|
303 |
+
## protoVisionXLhighFidelity3D_beta0520bakedVAE
|
304 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
305 |
+
|
306 |
+
## realityCheckXL_alpha11
|
307 |
+
β
Text encoder available. Difference by 0.001953125
|
308 |
+
|
309 |
+
## realmixXL_v10
|
310 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
311 |
+
|
312 |
+
## reproductionSDXL_v31
|
313 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
314 |
+
|
315 |
+
## runDiffusionXL_beta
|
316 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
317 |
+
|
318 |
+
## samaritan3DCartoon_v40sdxl
|
319 |
+
β
Text encoder available. Difference by 0.001953125
|
320 |
+
|
321 |
+
## sdvn6realXL_detailFace
|
322 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
323 |
+
|
324 |
+
## sdvn7realArtXL_beta2
|
325 |
+
β
Text encoder available. Difference by 0.001953125
|
326 |
+
|
327 |
+
## sdxl10arienMixXLasian_v10
|
328 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
329 |
+
|
330 |
+
## sdxlBaseNSFWFaces_sdxlNSFWFaces03
|
331 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
332 |
+
|
333 |
+
## sdxlFaeTastic_v10
|
334 |
+
β
Text encoder available. Difference by 0.001953125
|
335 |
+
|
336 |
+
## sdxlFixedVAEfp16Remove_baseFxiedVAEv2fp16
|
337 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
338 |
+
|
339 |
+
## sdxlNijiV4_sdxlNijiV4
|
340 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
341 |
+
|
342 |
+
## sdxlRonghua_v11
|
343 |
+
β
Text encoder available. Difference by 0.001953125
|
344 |
+
|
345 |
+
## sdxlUnstableDiffusers_v5UnchainedSlayer
|
346 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
347 |
+
|
348 |
+
## sdxlYamersAnimeUltra_yamersAnimeV2
|
349 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
350 |
+
|
351 |
+
## shikiAnimeXL_v10
|
352 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
353 |
+
|
354 |
+
## spectrumBlendX_v10
|
355 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
356 |
+
|
357 |
+
## stableDiffusionXL_v30
|
358 |
+
β
Text encoder available. Difference by 0.001953125
|
359 |
+
|
360 |
+
## talMendoXlsdXL_v11beta
|
361 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
362 |
+
|
363 |
+
## wizard_v10
|
364 |
+
β
Text encoder available. Difference by 0.001953125
|
365 |
+
|
366 |
+
## wyvernMix15XL_XLv11
|
367 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
368 |
+
|
369 |
+
## xl13asmodeusSFWNSFW_v17bakedVAEfp16fix
|
370 |
+
β
Text encoder available. Difference by 0.001953125
|
371 |
+
|
372 |
+
## xl3experimentalSD10XL_v10
|
373 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
374 |
+
|
375 |
+
## xl6hephaistosSD10XLsfw_v21bakedVAEfp16fix
|
376 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
377 |
+
|
378 |
+
## xlPerfectDesign_v2UltimateArtwork
|
379 |
+
β
Text encoder available. Difference by 0.001953125
|
380 |
+
|
381 |
+
## xlYamersRealistic_v3
|
382 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|
383 |
+
|
384 |
+
## xxMix9RealisticSDXL_Testv20
|
385 |
+
β
Text encoder available. Difference by 0.001953125
|
386 |
+
|
387 |
+
## zavyChromaXL_b2
|
388 |
+
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
|