zakarianasim073 commited on
Commit
aa12de4
·
1 Parent(s): 12a30c6

Fix requirements.txt and add ONNX Runtime

Browse files
Files changed (2) hide show
  1. README.md +41 -79
  2. requirements.txt +16 -44
README.md CHANGED
@@ -1,23 +1,12 @@
1
- ---
2
- title: Roop_unleashed4.3.2
3
- emoji: 💩
4
- colorFrom: green
5
- colorTo: blue
6
- sdk: gradio
7
- sdk_version: 5.4.0
8
- app_file: run.py
9
- pinned: false
10
- license: apache-2.0
11
- ---
12
  # roop-unleashed
13
 
14
- [Changelog](#changelog) [Usage](#usage) [Wiki](https://github.com/C0untFloyd/roop-unleashed/wiki)
15
 
 
16
 
17
- Uncensored Deepfakes for images and videos without training and an easy-to-use GUI.
18
-
19
 
20
- ![Screen](https://github.com/C0untFloyd/roop-unleashed/assets/131583554/6ee6860d-efbe-4337-8c62-a67598863637)
21
 
22
  ### Features
23
 
@@ -35,7 +24,6 @@ Uncensored Deepfakes for images and videos without training and an easy-to-use G
35
 
36
  and lots more...
37
 
38
-
39
  ## Disclaimer
40
 
41
  This project is for technical and academic use only.
@@ -44,40 +32,15 @@ Users of this software are expected to use this software responsibly while abidi
44
 
45
  In the event of violation of the legal and ethical requirements of the user's country or region, this code repository is exempt from liability
46
 
47
- Note: # Roop-Unleashed (Hugging Face Space)
48
-
49
- This Space runs Roop-Unleashed with a Gradio interface.
50
-
51
- ---
52
-
53
- ## ⚙️ Runtime Configuration
54
-
55
- We explicitly set the Python runtime to **3.10** using a `runtime.txt` file:
56
-
57
- ### Why Python 3.10?
58
- - Hugging Face Spaces default to Python 3.13.
59
- - Several dependencies (e.g., `torch==2.1.2`, `numpy==1.26.4`) do not yet provide wheels for Python 3.13.
60
- - For compatibility and stability, we pinned the runtime to Python 3.10, which is widely supported by ML libraries.
61
-
62
- ---
63
-
64
- ## 📦 Dependencies
65
-
66
- All dependencies are pinned in `requirements.txt` to avoid conflicts:
67
-
68
-
69
-
70
-
71
  ### Installation
72
 
73
  Please refer to the [wiki](https://github.com/C0untFloyd/roop-unleashed/wiki).
74
 
75
  #### macOS Installation
76
- Simply run the following command. It will check and install all dependencies if necessary.
77
-
78
- `/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/PJF16/roop-unleashed/master/installer/macOSinstaller.sh)`
79
 
 
80
 
 
81
 
82
  ### Usage
83
 
@@ -85,6 +48,7 @@ Simply run the following command. It will check and install all dependencies if
85
  - Linux: `python run.py`
86
  - macOS: `sh runMacOS.sh`
87
  - Dockerfile:
 
88
  ```shell
89
  docker build -t roop-unleashed . && docker run -t \
90
  -p 7860:7860 \
@@ -95,19 +59,34 @@ Simply run the following command. It will check and install all dependencies if
95
  roop-unleashed
96
  ```
97
 
98
- <a target="_blank" href="https://colab.research.google.com/github/C0untFloyd/roop-unleashed/blob/main/roop-unleashed.ipynb">
99
- <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
100
- </a>
101
-
102
-
103
  Additional commandline arguments are currently unsupported and settings should be done via the UI.
104
 
105
  > Note: When you run this program for the first time, it will download some models roughly ~2Gb in size.
106
 
 
107
 
 
108
 
 
 
 
 
109
 
110
- ### Changelog
 
 
 
 
 
 
 
 
 
 
 
 
 
 
111
 
112
  **28.9.2024** v4.3.1
113
 
@@ -116,7 +95,6 @@ Additional commandline arguments are currently unsupported and settings should b
116
  - New swapping mode "All input faces"
117
  - Average total fps displayed and setting for autorun
118
 
119
-
120
  **16.9.2024** v4.2.8
121
 
122
  - Bugfix: Starting roop-unleashed without NVIDIA gpu but cuda option enabled
@@ -126,7 +104,6 @@ Additional commandline arguments are currently unsupported and settings should b
126
  - Source Files Component cleared after face detection to release temp files
127
  - Added masking and mouth restore options to virtual cam
128
 
129
-
130
  **9.9.2024** v4.2.3
131
 
132
  - Hotfix for gradio pydantic issue with fastapi
@@ -136,7 +113,6 @@ Additional commandline arguments are currently unsupported and settings should b
136
  - Hardcoded image output format for livecam to jpeg - might be faster than previous webp
137
  - Chain events to be only executed if previous was a success
138
 
139
-
140
  **5.9.2024** v4.2.0
141
 
142
  - Added ability to move input & target faces order
@@ -147,18 +123,15 @@ Additional commandline arguments are currently unsupported and settings should b
147
  - Added CLI Arguments --server_share and --cuda_device_id
148
  - Added webp image support
149
 
150
-
151
  **15.07.2024** v4.1.1
152
 
153
  - Bugfix: Post-processing after swapping
154
 
155
-
156
  **14.07.2024** v4.1.0
157
 
158
  - Added subsample upscaling to increase swap resolution
159
  - Upgraded gradio
160
 
161
-
162
  **12.05.2024** v4.0.0
163
 
164
  - Bugfix: Unnecessary init every frame in live-cam
@@ -172,7 +145,6 @@ Additional commandline arguments are currently unsupported and settings should b
172
  - Added complete frame processing to extras tab
173
  - Colorize, upscale and misc filters added
174
 
175
-
176
  **22.04.2024** v3.9.0
177
 
178
  - Bugfix: Face detection bounding box corrupt values at weird angles
@@ -184,7 +156,6 @@ Additional commandline arguments are currently unsupported and settings should b
184
  - Face masking only runs when there is a face detected
185
  - Removed unnecessary toggle checkbox for text masking
186
 
187
-
188
  **22.03.2024** v3.6.5
189
 
190
  - Bugfix: Installer pulling latest update on first installation
@@ -192,7 +163,6 @@ Additional commandline arguments are currently unsupported and settings should b
192
  - Exposed erosion and blur amounts to UI
193
  - Using same values for manual masking too
194
 
195
-
196
  **20.03.2024** v3.6.3
197
 
198
  - Bugfix: Workaround for Gradio Slider Change Bug
@@ -201,7 +171,6 @@ Additional commandline arguments are currently unsupported and settings should b
201
  - Show offset mask as overlay
202
  - Changed layout for masking
203
 
204
-
205
  **18.03.2024** v3.6.0
206
 
207
  - Updated to Gradio 4.21.0 - requiring many changes under the hood
@@ -211,7 +180,6 @@ Additional commandline arguments are currently unsupported and settings should b
211
  - Removed unnecessary activate live-cam option
212
  - Added time info to preview frame and changed frame slider event to allow faster changes
213
 
214
-
215
  **10.03.2024** v3.5.5
216
 
217
  - Bugfix: Installer Path Env
@@ -222,16 +190,13 @@ Additional commandline arguments are currently unsupported and settings should b
222
  - Live Cam recoded to run separate from virtual cam and without blocking controls
223
  - Swapping with only 1 target face allows selecting from several input faces
224
 
225
-
226
-
227
  **08.01.2024** v3.5.0
228
 
229
  - Bugfix: wrong access options when creating folders
230
- - New auto rotation of horizontal faces, fixing bad landmark positions (expanded on ![PR 364](https://github.com/C0untFloyd/roop-unleashed/pull/364))
231
  - Simple VR Option for stereo Images/Movies, best used in selected face mode
232
  - Added RestoreFormer Enhancer - https://github.com/wzhouxiff/RestoreFormer
233
- - Bumped up package versions for onnx/Torch etc.
234
-
235
 
236
  **16.10.2023** v3.3.4
237
 
@@ -249,21 +214,18 @@ Initial Gradio Version - old TkInter Version now deprecated
249
  - Updated readme for new gradio version
250
  - Updated Colab
251
 
252
-
253
  # Acknowledgements
254
 
255
  Lots of ideas, code or pre-trained models borrowed from the following projects:
256
 
257
- https://github.com/deepinsight/insightface<br />
258
- https://github.com/s0md3v/roop<br />
259
- https://github.com/AUTOMATIC1111/stable-diffusion-webui<br />
260
- https://github.com/Hillobar/Rope<br />
261
- https://github.com/TencentARC/GFPGAN<br />
262
- https://github.com/kadirnar/codeformer-pip<br />
263
- https://github.com/csxmli2016/DMDNet<br />
264
- https://github.com/glucauze/sd-webui-faceswaplab<br />
265
- https://github.com/ykk648/face_power<br />
266
-
267
- <br />
268
- <br />
269
- Thanks to all developers!
 
 
 
 
 
 
 
 
 
 
 
 
1
  # roop-unleashed
2
 
3
+ This is **unofficial** mirror of repository
4
 
5
+ Models: <https://codeberg.org/roop-unleashed/models>
6
 
7
+ [Changelog](#changelog) [Usage](#usage)
 
8
 
9
+ Uncensored Deepfakes for images and videos without training and an easy-to-use GUI.
10
 
11
  ### Features
12
 
 
24
 
25
  and lots more...
26
 
 
27
  ## Disclaimer
28
 
29
  This project is for technical and academic use only.
 
32
 
33
  In the event of violation of the legal and ethical requirements of the user's country or region, this code repository is exempt from liability
34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  ### Installation
36
 
37
  Please refer to the [wiki](https://github.com/C0untFloyd/roop-unleashed/wiki).
38
 
39
  #### macOS Installation
 
 
 
40
 
41
+ Simply run the following command. It will check and install all dependencies if necessary.
42
 
43
+ `/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/PJF16/roop-unleashed/master/installer/macOSinstaller.sh)"`
44
 
45
  ### Usage
46
 
 
48
  - Linux: `python run.py`
49
  - macOS: `sh runMacOS.sh`
50
  - Dockerfile:
51
+
52
  ```shell
53
  docker build -t roop-unleashed . && docker run -t \
54
  -p 7860:7860 \
 
59
  roop-unleashed
60
  ```
61
 
 
 
 
 
 
62
  Additional commandline arguments are currently unsupported and settings should be done via the UI.
63
 
64
  > Note: When you run this program for the first time, it will download some models roughly ~2Gb in size.
65
 
66
+ ### Changelog
67
 
68
+ **03.01.2025** v4.4.1
69
 
70
+ Bugfix: Extras Tab
71
+ Bugfix: Preview Mask
72
+ Bugfix: DMDNet working on Cuda only
73
+ Updated Colab Script to also install CUDNN
74
 
75
+ **31.12.2024** v4.4.0 Hotfix
76
+
77
+ Bugfix: Updated Colab to use present Cuda Drivers
78
+ Bugfix: Live-Cam not working because of new face swapper
79
+ Set default swapping model back to Insightface
80
+
81
+ Happy New Year!
82
+
83
+ **30.12.2024** v4.4.0
84
+
85
+ - Added random face selection mode
86
+ - Added alternative face swapping model with 128px & 256 px output ([ReSwapper](https://github.com/somanchiu/ReSwapper/tree/main))
87
+ - Video repair added to Extras Tab
88
+ - Updated most packages to newer versions. CUDA >= 12.4 now required!
89
+ - Several minor bugfixes and QoL Changes
90
 
91
  **28.9.2024** v4.3.1
92
 
 
95
  - New swapping mode "All input faces"
96
  - Average total fps displayed and setting for autorun
97
 
 
98
  **16.9.2024** v4.2.8
99
 
100
  - Bugfix: Starting roop-unleashed without NVIDIA gpu but cuda option enabled
 
104
  - Source Files Component cleared after face detection to release temp files
105
  - Added masking and mouth restore options to virtual cam
106
 
 
107
  **9.9.2024** v4.2.3
108
 
109
  - Hotfix for gradio pydantic issue with fastapi
 
113
  - Hardcoded image output format for livecam to jpeg - might be faster than previous webp
114
  - Chain events to be only executed if previous was a success
115
 
 
116
  **5.9.2024** v4.2.0
117
 
118
  - Added ability to move input & target faces order
 
123
  - Added CLI Arguments --server_share and --cuda_device_id
124
  - Added webp image support
125
 
 
126
  **15.07.2024** v4.1.1
127
 
128
  - Bugfix: Post-processing after swapping
129
 
 
130
  **14.07.2024** v4.1.0
131
 
132
  - Added subsample upscaling to increase swap resolution
133
  - Upgraded gradio
134
 
 
135
  **12.05.2024** v4.0.0
136
 
137
  - Bugfix: Unnecessary init every frame in live-cam
 
145
  - Added complete frame processing to extras tab
146
  - Colorize, upscale and misc filters added
147
 
 
148
  **22.04.2024** v3.9.0
149
 
150
  - Bugfix: Face detection bounding box corrupt values at weird angles
 
156
  - Face masking only runs when there is a face detected
157
  - Removed unnecessary toggle checkbox for text masking
158
 
 
159
  **22.03.2024** v3.6.5
160
 
161
  - Bugfix: Installer pulling latest update on first installation
 
163
  - Exposed erosion and blur amounts to UI
164
  - Using same values for manual masking too
165
 
 
166
  **20.03.2024** v3.6.3
167
 
168
  - Bugfix: Workaround for Gradio Slider Change Bug
 
171
  - Show offset mask as overlay
172
  - Changed layout for masking
173
 
 
174
  **18.03.2024** v3.6.0
175
 
176
  - Updated to Gradio 4.21.0 - requiring many changes under the hood
 
180
  - Removed unnecessary activate live-cam option
181
  - Added time info to preview frame and changed frame slider event to allow faster changes
182
 
 
183
  **10.03.2024** v3.5.5
184
 
185
  - Bugfix: Installer Path Env
 
190
  - Live Cam recoded to run separate from virtual cam and without blocking controls
191
  - Swapping with only 1 target face allows selecting from several input faces
192
 
 
 
193
  **08.01.2024** v3.5.0
194
 
195
  - Bugfix: wrong access options when creating folders
196
+ - New auto rotation of horizontal faces, fixing bad landmark positions (expanded on PR 364)
197
  - Simple VR Option for stereo Images/Movies, best used in selected face mode
198
  - Added RestoreFormer Enhancer - https://github.com/wzhouxiff/RestoreFormer
199
+ - Bumped up package versions for onnx/Torch etc.
 
200
 
201
  **16.10.2023** v3.3.4
202
 
 
214
  - Updated readme for new gradio version
215
  - Updated Colab
216
 
 
217
  # Acknowledgements
218
 
219
  Lots of ideas, code or pre-trained models borrowed from the following projects:
220
 
221
+ https://github.com/deepinsight/insightface<br/>
222
+ https://github.com/s0md3v/roop<br/>
223
+ https://github.com/AUTOMATIC1111/stable-diffusion-webui<br/>
224
+ https://github.com/Hillobar/Rope<br/>
225
+ https://github.com/TencentARC/GFPGAN<br/>
226
+ https://github.com/kadirnar/codeformer-pip<br/>
227
+ https://github.com/csxmli2016/DMDNet<br/>
228
+ https://github.com/glucauze/sd-webui-faceswaplab<br/>
229
+ https://github.com/ykk648/face_power<br/>
230
+
231
+ Thanks to all developers!
 
 
requirements.txt CHANGED
@@ -1,48 +1,20 @@
1
  --extra-index-url https://download.pytorch.org/whl/cu124
2
- numpy
3
- opencv-python-headless
4
- onnx
5
- insightface
6
- albucore
7
- psutil
8
- torch; sys_platform != 'darwin'
9
- torch; sys_platform == 'darwin'
10
- torchvision; sys_platform != 'darwin'
11
- torchvision; sys_platform == 'darwin'
12
- onnxruntime; sys_platform == 'darwin' and platform_machine != 'arm64'
13
- onnxruntime-silicon; sys_platform == 'darwin' and platform_machine == 'arm64'
14
- onnxruntime-gpu; sys_platform != 'darwin'
15
- tqdm
 
16
  ftfy
17
  regex
18
  pyvirtualcam
19
- pydantic
20
- gradio
21
- huggingface_hub>=0.25.0
22
-
23
- # Core UI framework
24
- gradio[oauth,mcp]
25
-
26
- # Hugging Face integration
27
- huggingface_hub
28
- spaces
29
-
30
- # Deep learning stack
31
- torch
32
- torchvision
33
-
34
- # Image/video processing
35
- opencv-python
36
- numpy
37
- Pillow
38
-
39
- # Web server & networking
40
- uvicorn
41
- websockets
42
-
43
- # Utilities
44
- protobuf
45
- click
46
-
47
- # If roop is external, uncomment the next line:
48
- # git+https://github.com/s0md3v/roop.git
 
1
  --extra-index-url https://download.pytorch.org/whl/cu124
2
+ numpy==1.26.4
3
+ gradio==5.9.1
4
+ opencv-python-headless==4.10.0.84
5
+ onnx==1.16.1
6
+ insightface==0.7.3
7
+ albucore==0.0.16
8
+ psutil==5.9.6
9
+ torch==2.5.1+cu124; sys_platform != 'darwin'
10
+ torch==2.5.1; sys_platform == 'darwin'
11
+ torchvision==0.20.1+cu124; sys_platform != 'darwin'
12
+ torchvision==0.20.1; sys_platform == 'darwin'
13
+ onnxruntime==1.20.1; sys_platform == 'darwin' and platform_machine != 'arm64'
14
+ onnxruntime-silicon==1.20.1; sys_platform == 'darwin' and platform_machine == 'arm64'
15
+ onnxruntime-gpu==1.20.1; sys_platform != 'darwin'
16
+ tqdm==4.66.4
17
  ftfy
18
  regex
19
  pyvirtualcam
20
+ pydantic==2.10.4