Instructions to use XGENlabs/XGEN-JING with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use XGENlabs/XGEN-JING with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("XGENlabs/XGEN-JING", 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
Demo for this model on Spaces
Hi @XGENlabs 🤗
I'm Apolinario, from the open-source team at Hugging Face. Congrats and thanks for open-sourcing XGENlabs/XGEN-JING on the Hub! We were excited about this work and built with an agent an interactive demo app of it on Hugging Face Spaces, running on a free ZeroGPU infrastructure.
Here's a link to the demo: https://huggingface.co/spaces/hugging-apps/xgen-jing-demo
We would love to transfer this demo to you or your organization. Would you like this demo to live under your own account or organization? If so just let me know here which username to transfer to, and we'll transfer the Space over to you, we hope it can give your work more visibility, discoverability and allows folks to try it out.
(If you have any questions or just want to chat more about this, you can find me on Twitter, LinkedIn or apolinario @ huggingface.co)
Cheers,
Poli
Hi Poli,
Thank you so much for building this demo for XGEN-JING. We really appreciate the support and the initiative from the Hugging Face team.
We’d be happy to have the Space transferred to our account. You can transfer it directly to our existing XGEN account.
We also tried the demo and have a few suggestions that could make it more flexible for users:
- Add a 768-resolution inference option, so users can choose between different output resolutions.
- Make the generation duration configurable, allowing users to select the desired sequence length.
- Make PE optional, so users can choose whether to enable it during inference.
If helpful, we’d also be happy to connect directly and collaborate on further improvements to the demo. Our team can support the implementation and provide any model-side details as needed.
Thanks again for putting this together and for helping make XGEN-JING more accessible to the community.
Best,
Tressi
XGEN Labs
tressi.tian@xgenlabs.ai
Hey @xgenlabs !
Thank you for open sourcing XGEN-JING!
Transferred to: https://huggingface.co/spaces/XGENlabs/xgen-jing-demo with a ZeroGPU grant
Free to post about, put the demo on the project page, reference it on repos, etc. as you wish
Also feel more than free to take ownership and make modifications as you see fit. For future releases from you, would be great if they already came with a demos! You can use this one as a blueprint to build by yourself or with the help of an agent, you can load the huggingface-spaces skill on Claude Code, Codex, Hermes, Pi, etc.
Cheers,
Poli
Feel free to apply the fixes/suggestions you mention now that you have the demo ownershiP!