update README.md

README.md

@@ -1,13 +1,24 @@
+---
+title: Roop_unleashed4.3.2
+emoji: 💩
+colorFrom: green
+colorTo: blue
+sdk: gradio
+sdk_version: 5.4.0
+app_file: run.py
+pinned: false
+license: apache-2.0
+---
 # roop-unleashed
 
-This is **unofficial** mirror of repository
+[Changelog](#changelog) • [Usage](#usage) • [Wiki](https://github.com/C0untFloyd/roop-unleashed/wiki)
 
-Models: <https://codeberg.org/roop-unleashed/models>
-
-[Changelog](#changelog) • [Usage](#usage)
 
 Uncensored Deepfakes for images and videos without training and an easy-to-use GUI.
 
+
+![Screen](https://github.com/C0untFloyd/roop-unleashed/assets/131583554/6ee6860d-efbe-4337-8c62-a67598863637)
+
 ### Features
 
 - Platform-independant Browser GUI
@@ -24,6 +35,7 @@ Uncensored Deepfakes for images and videos without training and an easy-to-use G
 
 and lots more...
 
+
 ## Disclaimer
 
 This project is for technical and academic use only.
@@ -32,15 +44,40 @@ Users of this software are expected to use this software responsibly while abidi
 
 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
 
+Note: # Roop-Unleashed (Hugging Face Space)
+
+This Space runs Roop-Unleashed with a Gradio interface.
+
+---
+
+## ⚙️ Runtime Configuration
+
+We explicitly set the Python runtime to **3.10** using a `runtime.txt` file:
+
+### Why Python 3.10?
+- Hugging Face Spaces default to Python 3.13.
+- Several dependencies (e.g., `torch==2.1.2`, `numpy==1.26.4`) do not yet provide wheels for Python 3.13.
+- For compatibility and stability, we pinned the runtime to Python 3.10, which is widely supported by ML libraries.
+
+---
+
+## 📦 Dependencies
+
+All dependencies are pinned in `requirements.txt` to avoid conflicts:
+
+
+
+
 ### Installation
 
 Please refer to the [wiki](https://github.com/C0untFloyd/roop-unleashed/wiki).
 
 #### macOS Installation
-
 Simply run the following command. It will check and install all dependencies if necessary.
 
-`/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/PJF16/roop-unleashed/master/installer/macOSinstaller.sh)"`
+`/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/PJF16/roop-unleashed/master/installer/macOSinstaller.sh)`
+
+
 
 ### Usage
 
@@ -48,7 +85,6 @@ Simply run the following command. It will check and install all dependencies if
 - Linux: `python run.py`
 - macOS: `sh runMacOS.sh`
 - Dockerfile:
-
   ```shell
   docker build -t roop-unleashed . && docker run -t \
     -p 7860:7860 \
@@ -59,34 +95,19 @@ Simply run the following command. It will check and install all dependencies if
     roop-unleashed
   ```
 
+<a target="_blank" href="https://colab.research.google.com/github/C0untFloyd/roop-unleashed/blob/main/roop-unleashed.ipynb">
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
+</a>
+  
+
 Additional commandline arguments are currently unsupported and settings should be done via the UI.
 
 > Note: When you run this program for the first time, it will download some models roughly ~2Gb in size.
 
-### Changelog
-
-**03.01.2025** v4.4.1
-
-Bugfix: Extras Tab
-Bugfix: Preview Mask
-Bugfix: DMDNet working on Cuda only
-Updated Colab Script to also install CUDNN
 
-**31.12.2024** v4.4.0 Hotfix
 
-Bugfix: Updated Colab to use present Cuda Drivers
-Bugfix: Live-Cam not working because of new face swapper
-Set default swapping model back to Insightface
 
-Happy New Year!
-
-**30.12.2024** v4.4.0
-
-- Added random face selection mode
-- Added alternative face swapping model with 128px & 256 px output ([ReSwapper](https://github.com/somanchiu/ReSwapper/tree/main))
-- Video repair added to Extras Tab
-- Updated most packages to newer versions. CUDA >= 12.4 now required!
-- Several minor bugfixes and QoL Changes
+### Changelog
 
 **28.9.2024** v4.3.1
 
@@ -95,6 +116,7 @@ Happy New Year!
 - New swapping mode "All input faces"
 - Average total fps displayed and setting for autorun
 
+
 **16.9.2024** v4.2.8
 
 - Bugfix: Starting roop-unleashed without NVIDIA gpu but cuda option enabled
@@ -104,6 +126,7 @@ Happy New Year!
 - Source Files Component cleared after face detection to release temp files
 - Added masking and mouth restore options to virtual cam
 
+
 **9.9.2024** v4.2.3
 
 - Hotfix for gradio pydantic issue with fastapi
@@ -113,6 +136,7 @@ Happy New Year!
 - Hardcoded image output format for livecam to jpeg - might be faster than previous webp
 - Chain events to be only executed if previous was a success
 
+
 **5.9.2024** v4.2.0
 
 - Added ability to move input & target faces order
@@ -123,15 +147,18 @@ Happy New Year!
 - Added CLI Arguments --server_share and --cuda_device_id
 - Added webp image support
 
+
 **15.07.2024** v4.1.1
 
 - Bugfix: Post-processing after swapping
 
+
 **14.07.2024** v4.1.0
 
 - Added subsample upscaling to increase swap resolution
 - Upgraded gradio
 
+
 **12.05.2024** v4.0.0
 
 - Bugfix: Unnecessary init every frame in live-cam
@@ -145,6 +172,7 @@ Happy New Year!
 - Added complete frame processing to extras tab
 - Colorize, upscale and misc filters added
 
+
 **22.04.2024** v3.9.0
 
 - Bugfix: Face detection bounding box corrupt values at weird angles
@@ -156,6 +184,7 @@ Happy New Year!
 - Face masking only runs when there is a face detected
 - Removed unnecessary toggle checkbox for text masking
 
+
 **22.03.2024** v3.6.5
 
 - Bugfix: Installer pulling latest update on first installation
@@ -163,6 +192,7 @@ Happy New Year!
 - Exposed erosion and blur amounts to UI
 - Using same values for manual masking too
 
+
 **20.03.2024** v3.6.3
 
 - Bugfix: Workaround for Gradio Slider Change Bug
@@ -171,6 +201,7 @@ Happy New Year!
 - Show offset mask as overlay
 - Changed layout for masking
 
+
 **18.03.2024** v3.6.0
 
 - Updated to Gradio 4.21.0 - requiring many changes under the hood
@@ -180,6 +211,7 @@ Happy New Year!
 - Removed unnecessary activate live-cam option
 - Added time info to preview frame and changed frame slider event to allow faster changes
 
+
 **10.03.2024** v3.5.5
 
 - Bugfix: Installer Path Env
@@ -190,13 +222,16 @@ Happy New Year!
 - Live Cam recoded to run separate from virtual cam and without blocking controls
 - Swapping with only 1 target face allows selecting from several input faces
 
+
+
 **08.01.2024** v3.5.0
 
 - Bugfix: wrong access options when creating folders
-- New auto rotation of horizontal faces, fixing bad landmark positions (expanded on PR 364)
+- New auto rotation of horizontal faces, fixing bad landmark positions (expanded on ![PR 364](https://github.com/C0untFloyd/roop-unleashed/pull/364))
 - Simple VR Option for stereo Images/Movies, best used in selected face mode
 - Added RestoreFormer Enhancer - https://github.com/wzhouxiff/RestoreFormer
-- Bumped up package versions for onnx/Torch etc.
+- Bumped up package versions for onnx/Torch etc.   
+
 
 **16.10.2023** v3.3.4
 
@@ -214,18 +249,21 @@ Initial Gradio Version - old TkInter Version now deprecated
 - Updated readme for new gradio version
 - Updated Colab
 
+
 # Acknowledgements
 
 Lots of ideas, code or pre-trained models borrowed from the following projects:
 
-https://github.com/deepinsight/insightface<br/>
-https://github.com/s0md3v/roop<br/>
-https://github.com/AUTOMATIC1111/stable-diffusion-webui<br/> 
-https://github.com/Hillobar/Rope<br/>
-https://github.com/TencentARC/GFPGAN<br/>
-https://github.com/kadirnar/codeformer-pip<br/>
-https://github.com/csxmli2016/DMDNet<br/>
-https://github.com/glucauze/sd-webui-faceswaplab<br/>
-https://github.com/ykk648/face_power<br/>
-
-Thanks to all developers!
+https://github.com/deepinsight/insightface<br />
+https://github.com/s0md3v/roop<br />
+https://github.com/AUTOMATIC1111/stable-diffusion-webui<br /> 
+https://github.com/Hillobar/Rope<br />
+https://github.com/TencentARC/GFPGAN<br />   
+https://github.com/kadirnar/codeformer-pip<br />
+https://github.com/csxmli2016/DMDNet<br />
+https://github.com/glucauze/sd-webui-faceswaplab<br />
+https://github.com/ykk648/face_power<br />
+
+<br />
+<br />
+Thanks to all developers!