WebUI for Image/Video generation

Supported Text-2-Image models

Video generation

Supported Image-2-Video models

Additional

SVDquant - Nunchaku

---

---

Installation guide for Windows

Step 1: Clone the repository

git clone https://github.com/newgenai79/sd-diffuser-webui

Step 2: Navigate inside the cloned repository

cd sd-diffuser-webui

Step 3: Create virtual environment: using conda/miniconda

conda create -n sddw python==3.11.9 -y

Step 4: Activate virtual environment

conda activate sddw

Step 5: Install requirements

pip install -r requirements.txt

Step 5a: Install SVDQuant/nunchaku requirements (optional)

pip install -r requirements_svdquant.txt

Step 5b: Install these if you want to use DWPose (optional)

pip install -U openmim

mim install mmcv==2.1.0

mim install mmpose==1.3.2

mim install mmdet==3.2.0

Step 6: Launch gradio based WebUI

python app.py

---

Test environment

• Windows 11
• Nvidia RTX 4060 8 GB Laptop GPU + 8 GB shared RAM + 45 GB Virtual memory / paging file size
• Python 3.10.11
• Miniconda
• Git
• CUDA 12.6 (Cuda compilation tools, release 12.6, V12.6.77 - Build cuda_12.6.r12.6/compiler.34841621_0)
• Microsoft (R) C/C++ Optimizing Compiler Version 19.29.30157 for x64

• Linux Mint 22 Wilma
• AMD Ryzen 5700 X3D + Nvidia Geforce RTX 4070 12 GB + 32 GB DDR4 RAM
• Python 3.11.9
• Miniconda
• Cuda V12.0.140 - Build cuda_12.0.r12.0/compiler.32267302_0

---

All models inherit the license of the original model.

---

Credits:
Huggingface/Diffusers team
Diffsynth Studio team
SVDQuant