Create 3D models from text or images with SD plugins
A custom extension to the Stable Diffusion WebUI for automatic generation of 3D models from text or images.
Generate 3D models from text or images with OpenAl Shap-E,
GitHub project address: https://github.com/jtydhr88/sd-webui-txt-img-to-3d-model
Installation steps :
- Select "Extensions -> Install from URL" in the extension center
- Paste the link to the repository
- Restart WebU after installing and applying
Instructions:
- First select "txt or "img" mode
- If you choose "txt" mode, you can enter the prompt text and then generate it (no need to upload an image). If you choose "img" mode, you can upload an image and then generate it (no need to enter a prompt text). For better performance, it is recommended to first convert the image The Background Removal preview window will display the latest generated model. If the batch size is greater than 1, you can view all generated files under the "extensionslsd-webui-txt-img-to-3d-modeloutputs" directory.
Install
Just like installing other extensions for webui:
1. Go to Extensions -> Install from URL
2. Paste this repo link
3. Install
4. Go to Installed, apply and restart the UI
About shap-E
Please go to OpenAl shap-E for more details.
how to use
1. First select the mode, txt or img.
2. Shap-E will download its model in the background for the first time, please check the progress through the console.
3. If you choose txt, you can enter a prompt and then generate (no need to upload a picture, it won't work)
4. If you choose img, you can upload a picture and then generate (no need to enter a prompt, it won't work).
5. For better performance, you need to remove the background from the image.
6. If the batch size > 1, the preview will show the latest generated files, you can go to extensionssd-webui-txt-img-to-3d.modeloutputs to
check the whole generated files.
Using SD's plug-in, you can create 3D models from text or pictures, and the effect looks good.
Create 3D models from text or images with SD plugins
A custom extension to the Stable Diffusion WebUI for automatic generation of 3D models from text or images.
Generate 3D models from text or images with OpenAl Shap-E,
GitHub project address: https://github.com/jtydhr88/sd-webui-txt-img-to-3d-model
Installation steps :
- Select "Extensions -> Install from URL" in the extension center
- Paste the link to the repository
- Restart WebU after installing and applying
Instructions:
- First select "txt or "img" mode
- If you choose "txt" mode, you can enter the prompt text and then generate it (no need to upload an image). If you choose "img" mode, you can upload an image and then generate it (no need to enter a prompt text). For better performance, it is recommended to first convert the image The Background Removal preview window will display the latest generated model. If the batch size is greater than 1, you can view all generated files under the "extensionslsd-webui-txt-img-to-3d-modeloutputs" directory.
