readme / license correction
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- stable-diffusion-xl
|
6 |
- stable-diffusion-xl-diffusers
|
@@ -69,6 +69,21 @@ The FFXL400 model is designed for a multitude of applications. Whether you're de
|
|
69 |
- Dive deep into weighting experiments with multiple LoRAs.
|
70 |
- Explore the nuances and intricacies of integrated LoRAs.
|
71 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
## π How to Use
|
73 |
|
74 |
The model can be easily integrated into your projects. Here's a quick guide on how to use the FFXL400 model:
|
@@ -89,13 +104,197 @@ The model can be easily integrated into your projects. Here's a quick guide on h
|
|
89 |
outputs = model(**inputs)
|
90 |
```
|
91 |
|
92 |
-
|
|
|
93 |
You can also use the FFXL400 as a starting point for further training. Simply load it into your training pipeline and proceed as you would with any other model.
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
|
95 |
## π Background
|
96 |
|
97 |
The FFXL400 is built upon the insights and data from the [400GB-LoraXL repository](https://huggingface.co/FFusion/400GB-LoraXL). Each LoRA in that collection was extracted using the Low-Rank Adaptation (LoRA) technique, providing a rich dataset for research and exploration. The FFXL400 is the pinnacle of that research, representing a harmonious blend of the best LoRAs.
|
98 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
99 |
---
|
100 |
|
101 |
We hope the FFXL400 serves as a valuable asset in your AI journey. We encourage feedback, contributions, and insights from the community to further refine and enhance this model. Together, let's push the boundaries of what's possible!
|
|
|
1 |
---
|
2 |
+
license: openrail++
|
3 |
+
base_model: FFusion/FFusionXL-BASE
|
4 |
tags:
|
5 |
- stable-diffusion-xl
|
6 |
- stable-diffusion-xl-diffusers
|
|
|
69 |
- Dive deep into weighting experiments with multiple LoRAs.
|
70 |
- Explore the nuances and intricacies of integrated LoRAs.
|
71 |
|
72 |
+
|
73 |
+
|
74 |
+
## β οΈ License & Usage Disclaimers
|
75 |
+
|
76 |
+
**Please review the full [license agreement](https://huggingface.co/FFusion/FFXL400/blob/main/LICENSE.md) before accessing or using the models.**
|
77 |
+
|
78 |
+
π΄ The models and weights available in this repository are **strictly for research and testing purposes**, with exceptions noted below. They are **not** generally intended for commercial use and are dependent on each individual LORA.
|
79 |
+
|
80 |
+
π΅ **Exception for Commercial Use:** The [FFusionXL-BASE](https://huggingface.co/FFusion/FFusionXL-BASE), [FFusion-BaSE](https://huggingface.co/FFusion/FFusion-BaSE), [di.FFUSION.ai-v2.1-768-BaSE-alpha](https://huggingface.co/FFusion/di.FFUSION.ai-v2.1-768-BaSE-alpha), and [di.ffusion.ai.Beta512](https://huggingface.co/FFusion/di.ffusion.ai.Beta512) models are trained by FFusion AI using images for which we hold licenses. Users are advised to primarily use these models for a safer experience. These particular models are allowed for commercial use.
|
81 |
+
|
82 |
+
π΄ **Disclaimer:** FFusion AI, in conjunction with Source Code Bulgaria Ltd and BlackswanTechnologies, **does not endorse or guarantee the content produced by the weights in each LORA**. There's potential for generating NSFW or offensive content. Collectively, we expressly disclaim responsibility for the outcomes and content produced by these weights.
|
83 |
+
|
84 |
+
π΄ **Acknowledgement:** The [FFusionXL-BASE](https://huggingface.co/FFusion/FFusionXL-BASE) model model is a uniquely developed version by FFusion AI. Rights to this and associated modifications belong to FFusion AI and Source Code Bulgaria Ltd. Ensure adherence to both this license and any conditions set by Stability AI Ltd for referenced models.
|
85 |
+
|
86 |
+
|
87 |
## π How to Use
|
88 |
|
89 |
The model can be easily integrated into your projects. Here's a quick guide on how to use the FFXL400 model:
|
|
|
104 |
outputs = model(**inputs)
|
105 |
```
|
106 |
|
107 |
+
## Further Training
|
108 |
+
|
109 |
You can also use the FFXL400 as a starting point for further training. Simply load it into your training pipeline and proceed as you would with any other model.
|
110 |
+
|
111 |
+
[Autotrain Advanced](https://github.com/huggingface/autotrain-advanced),
|
112 |
+
|
113 |
+
[Kohya + Stable Diffusion XL](https://huggingface.co/docs/diffusers/main/en/training/lora#stable-diffusion-xl),
|
114 |
+
|
115 |
+
|
116 |
|
117 |
## π Background
|
118 |
|
119 |
The FFXL400 is built upon the insights and data from the [400GB-LoraXL repository](https://huggingface.co/FFusion/400GB-LoraXL). Each LoRA in that collection was extracted using the Low-Rank Adaptation (LoRA) technique, providing a rich dataset for research and exploration. The FFXL400 is the pinnacle of that research, representing a harmonious blend of the best LoRAs.
|
120 |
|
121 |
+
|
122 |
+
## Library of Available LoRA Models π
|
123 |
+
|
124 |
+
![loraXL FFUsion](https://cdn-uploads.huggingface.co/production/uploads/6380cf05f496d57325c12194/XQlnis5W2-fgDnGZ60EK9.jpeg)
|
125 |
+
|
126 |
+
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"`:
|
127 |
+
|
128 |
+
```
|
129 |
+
lora_filename =
|
130 |
+
- FFai.0001.4Guofeng4xl_V1125d.lora_Dim64.safetensors
|
131 |
+
- FFai.0002.4Guofeng4xl_V1125d.lora_Dim8.safetensors
|
132 |
+
- FFai.0003.4Guofeng4xl_V1125d.loraa.safetensors
|
133 |
+
- FFai.0004.Ambiencesdxl_A1.lora.safetensors
|
134 |
+
- FFai.0005.Ambiencesdxl_A1.lora_8.safetensors
|
135 |
+
- FFai.0006.Angrasdxl10_V22.lora.safetensors
|
136 |
+
- FFai.0007.Animaginexl_V10.lora.safetensors
|
137 |
+
- FFai.0008.Animeartdiffusionxl_Alpha3.lora.safetensors
|
138 |
+
- FFai.0009.Astreapixiexlanime_V16.lora.safetensors
|
139 |
+
- FFai.0010.Bluepencilxl_V010.lora.safetensors
|
140 |
+
- FFai.0011.Bluepencilxl_V021.lora.safetensors
|
141 |
+
- FFai.0012.Breakdomainxl_V03d.lora.safetensors
|
142 |
+
- FFai.0013.Canvasxl_Bfloat16v002.lora.safetensors
|
143 |
+
- FFai.0014.Cherrypickerxl_V20.lora.safetensors
|
144 |
+
- FFai.0015.Copaxtimelessxlsdxl1_V44.lora.safetensors
|
145 |
+
- FFai.0016.Counterfeitxl-Ffusionai-Alpha-Vae.lora.safetensors
|
146 |
+
- FFai.0017.Counterfeitxl_V10.lora.safetensors
|
147 |
+
- FFai.0018.Crystalclearxl_Ccxl.lora.safetensors
|
148 |
+
- FFai.0019.Deepbluexl_V006.lora.safetensors
|
149 |
+
- FFai.0020.Dream-Ffusion-Shaper.lora.safetensors
|
150 |
+
- FFai.0021.Dreamshaperxl10_Alpha2xl10.lora.safetensors
|
151 |
+
- FFai.0022.Duchaitenaiartsdxl_V10.lora.safetensors
|
152 |
+
- FFai.0023.Dynavisionxlallinonestylized_Beta0371bakedvae.lora.safetensors
|
153 |
+
- FFai.0024.Dynavisionxlallinonestylized_Beta0411bakedvae.lora.safetensors
|
154 |
+
- FFai.0025.Fantasticcharacters_V55.lora.safetensors
|
155 |
+
- FFai.0026.Fenrisxl_V55.lora.safetensors
|
156 |
+
- FFai.0027.Fudukimix_V10.lora.safetensors
|
157 |
+
- FFai.0028.Infinianimexl_V16.lora.safetensors
|
158 |
+
- FFai.0029.Juggernautxl_Version1.lora_1.safetensors
|
159 |
+
- FFai.0030.Lahmysterioussdxl_V330.lora.safetensors
|
160 |
+
- FFai.0031.Mbbxlultimate_V10rc.lora.safetensors
|
161 |
+
- FFai.0032.Miamodelsfwnsfwsdxl_V30.lora.safetensors
|
162 |
+
- FFai.0033.Morphxl_V10.lora.safetensors
|
163 |
+
- FFai.0034.Nightvisionxlphotorealisticportrait_Beta0681bakedvae.lora_1.safetensors
|
164 |
+
- FFai.0035.Osorubeshialphaxl_Z.lora.safetensors
|
165 |
+
- FFai.0036.Physiogenxl_V04.lora.safetensors
|
166 |
+
- FFai.0037.Protovisionxlhighfidelity3d_Beta0520bakedvae.lora.safetensors
|
167 |
+
- FFai.0038.Realitycheckxl_Alpha11.lora.safetensors
|
168 |
+
- FFai.0039.Realmixxl_V10.lora.safetensors
|
169 |
+
- FFai.0040.Reproductionsdxl_V31.lora.safetensors
|
170 |
+
- FFai.0041.Rundiffusionxl_Beta.lora.safetensors
|
171 |
+
- FFai.0042.Samaritan3dcartoon_V40sdxl.lora.safetensors
|
172 |
+
- FFai.0043.Sdvn6realxl_Detailface.lora.safetensors
|
173 |
+
- FFai.0044.Sdvn7realartxl_Beta2.lora.safetensors
|
174 |
+
- FFai.0045.Sdxl10arienmixxlasian_V10.lora.safetensors
|
175 |
+
- FFai.0046.Sdxlbasensfwfaces_Sdxlnsfwfaces03.lora.safetensors
|
176 |
+
- FFai.0047.Sdxlfaetastic_V10.lora.safetensors
|
177 |
+
- FFai.0048.Sdxlfixedvaefp16remove_Basefxiedvaev2fp16.lora.safetensors
|
178 |
+
- FFai.0049.Sdxlnijiv4_Sdxlnijiv4.lora.safetensors
|
179 |
+
- FFai.0050.Sdxlronghua_V11.lora.safetensors
|
180 |
+
- FFai.0051.Sdxlunstablediffusers_V5unchainedslayer.lora.safetensors
|
181 |
+
- FFai.0052.Sdxlyamersanimeultra_Yamersanimev2.lora.safetensors
|
182 |
+
- FFai.0053.Shikianimexl_V10.lora.safetensors
|
183 |
+
- FFai.0054.Spectrumblendx_V10.lora.safetensors
|
184 |
+
- FFai.0055.Stablediffusionxl_V30.lora.safetensors
|
185 |
+
- FFai.0056.Talmendoxlsdxl_V11beta.lora.safetensors
|
186 |
+
- FFai.0057.Wizard_V10.lora.safetensors
|
187 |
+
- FFai.0058.Wyvernmix15xl_Xlv11.lora.safetensors
|
188 |
+
- FFai.0059.Xl13asmodeussfwnsfw_V17bakedvae.lora.safetensors
|
189 |
+
- FFai.0060.Xl3experimentalsd10xl_V10.lora.safetensors
|
190 |
+
- FFai.0061.Xl6hephaistossd10xlsfw_V21bakedvaefp16fix.lora.safetensors
|
191 |
+
- FFai.0062.Xlperfectdesign_V2ultimateartwork.lora.safetensors
|
192 |
+
- FFai.0063.Xlyamersrealistic_V3.lora.safetensors
|
193 |
+
- FFai.0064.Xxmix9realisticsdxl_Testv20.lora.safetensors
|
194 |
+
- FFai.0065.Zavychromaxl_B2.lora.safetensors
|
195 |
+
|
196 |
+
```
|
197 |
+
|
198 |
+
## π Acknowledgements & Citations
|
199 |
+
|
200 |
+
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!
|
201 |
+
|
202 |
+
We would also like to acknowledge and give credit to the following projects and authors:
|
203 |
+
|
204 |
+
- **ComfyUI**: We've used and modified portions of [ComfyUI](https://github.com/comfyanonymous/ComfyUI) for our work.
|
205 |
+
- **kohya-ss/sd-scripts and bmaltais**: Our work also incorporates modifications from [kohya-ss/sd-scripts](https://github.com/kohya-ss/sd-scripts).
|
206 |
+
- **lora-inspector**: We've benefited from the [lora-inspector](https://github.com/rockerBOO/lora-inspector) project.
|
207 |
+
- **KohakuBlueleaf**: Special mention to KohakuBlueleaf for their invaluable contributions.
|
208 |
+
|
209 |
+
|
210 |
+
[![400GB FFusion Lora XL 5](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image5sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image5.jpg)
|
211 |
+
|
212 |
+
[![400GB FFusion Lora XL 6](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image6sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image6.jpg)
|
213 |
+
|
214 |
+
[![400GB FFusion Lora XL 7](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image7sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image7.jpg)
|
215 |
+
|
216 |
+
[![400GB FFusion Lora XL 9](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image9.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/tree/main)
|
217 |
+
|
218 |
+
|
219 |
+
### HowMuch ???
|
220 |
+
![60% Works](https://img.shields.io/badge/60%25%20of%20the%20Time-It%20Works%20Every%20Time-green)
|
221 |
+
|
222 |
+
|
223 |
+
**Have you ever asked yourself, "How much space have I wasted on `*.ckpt` and `*.safetensors` checkpoints?"** π€
|
224 |
+
Say hello to HowMuch: Checking checkpoint wasted space since... well, now!
|
225 |
+
|
226 |
+
π Enjoy this somewhat unnecessary, yet **"fun-for-the-whole-family"** DiskSpaceAnalyzer tool. π
|
227 |
+
|
228 |
+
## Overview
|
229 |
+
|
230 |
+
|
231 |
+
`HowMuch` is a Python tool designed to scan your drives (or a specified directory) and report on the total space used by files with specific extensions, mainly `.ckpt` and `.safetensors`.
|
232 |
+
|
233 |
+
It outputs:
|
234 |
+
- The total storage capacity of each scanned drive or directory.
|
235 |
+
- The space occupied by `.ckpt` and `.safetensors` files.
|
236 |
+
- The free space available.
|
237 |
+
- A neat bar chart visualizing the above data.
|
238 |
+
|
239 |
+
## Installation
|
240 |
+
[GitHub](https://github.com/1e-2/HowMuch)
|
241 |
+
|
242 |
+
### From PyPI
|
243 |
+
|
244 |
+
You can easily install `HowMuch` via pip:
|
245 |
+
|
246 |
+
```bash
|
247 |
+
pip install howmuch
|
248 |
+
```
|
249 |
+
|
250 |
+
### From Source
|
251 |
+
|
252 |
+
1. Clone the repository:
|
253 |
+
|
254 |
+
```bash
|
255 |
+
git clone https://github.com/1e-2/HowMuch.git
|
256 |
+
```
|
257 |
+
|
258 |
+
2. Navigate to the cloned directory and install:
|
259 |
+
|
260 |
+
```bash
|
261 |
+
cd HowMuch
|
262 |
+
pip install .
|
263 |
+
```
|
264 |
+
|
265 |
+
## Usage
|
266 |
+
|
267 |
+
|
268 |
+
Run the tool without any arguments to scan all drives:
|
269 |
+
|
270 |
+
```bash
|
271 |
+
howmuch
|
272 |
+
```
|
273 |
+
|
274 |
+
Or, specify a particular directory or drive to scan:
|
275 |
+
|
276 |
+
```bash
|
277 |
+
howmuch --scan C:
|
278 |
+
```
|
279 |
+
|
280 |
+
### π **Contact Information**
|
281 |
+
|
282 |
+
The **FFusion.ai** project is proudly maintained by **Source Code Bulgaria Ltd** & **Black Swan Technologies**.
|
283 |
+
|
284 |
+
π§ Reach us at [[email protected]](mailto:[email protected]) for any inquiries or support.
|
285 |
+
|
286 |
+
#### π **Find us on:**
|
287 |
+
|
288 |
+
- π [GitHub](https://github.com/1e-2)
|
289 |
+
- π [Hugging Face](https://huggingface.co/FFusion/)
|
290 |
+
- π‘ [Civitai](https://civitai.com/user/idle/models)
|
291 |
+
|
292 |
+
π **Security powered by** [Comodo.BG](http://Comodo.BG) & [Preasidium.CX](http://Preasidium.CX)
|
293 |
+
π Marketing by [ΠΡΠ³ΡΠ».com](http://ΠΡΠ³ΡΠ».com)
|
294 |
+
π© [![Email](https://img.shields.io/badge/Email-enquiries%40ffusion.ai-blue?style=for-the-badge&logo=gmail)](mailto:[email protected])
|
295 |
+
π Sofia Istanbul London
|
296 |
+
|
297 |
+
|
298 |
---
|
299 |
|
300 |
We hope the FFXL400 serves as a valuable asset in your AI journey. We encourage feedback, contributions, and insights from the community to further refine and enhance this model. Together, let's push the boundaries of what's possible!
|