Instructions to use akshan-main/modular-zimage-upscale with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use akshan-main/modular-zimage-upscale with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("akshan-main/modular-zimage-upscale", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Commercial use permission for Modular Z-Image Upscale
Hi Akshan,
First, thank you for sharing Modular Z-Image Upscale. I've been looking for a really good tiled/generative upscaling solution based on Z-Image, and I've spent quite a lot of time searching.
So far, I haven't found a ready alternative that does what I'm looking for as well as your project. I really like the approach you've taken with the tiled latent processing and blending, and I'd love to use it for my own workflow.
My goal is to use it commercially for creating stock images. Specifically, I would run the upscaler locally on AI-generated images and then submit/sell the resulting images on commercial stock platforms.
I noticed that the repository doesn't currently seem to have a clear license specifying whether commercial use is allowed, so I wanted to ask you directly before using it.
Would you be willing to give me permission to use Modular Z-Image Upscale commercially for this purpose?
In particular, I would like to:
Use the code locally for commercial work
Modify it or integrate it into my own application/workflow if needed, for my personal use only.
Use and commercially sell the resulting upscaled images on stock platforms
I completely understand if you have specific conditions or limitations. I just wanted to ask before proceeding, since I really like your work and haven't found another ready solution that fits what I'm looking for.
If you're okay with this, a simple confirmation here would be greatly appreciated so I can keep it as a record.
Thank you!
Feel free to use it but please cite this so more people can benefit from my work! Thank you! Do cite it with link!