Image-Text-to-Video
Diffusers
Safetensors
English
Chinese
xgen-jing
world-model
egocentric
video-generation
audio-video-generation
Instructions to use GSsmart/XGEN-GSsmart-JING with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use GSsmart/XGEN-GSsmart-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("GSsmart/XGEN-GSsmart-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
Download NOTICE from GSsmart/XGEN-GSsmart-JING: direct link, hf CLI and curl.
- Browser
- Download file 1.39 kB
-
https://huggingface.co/GSsmart/XGEN-GSsmart-JING/resolve/main/NOTICE
- Command line
-
hf download hf://GSsmart/XGEN-GSsmart-JING/NOTICE
-
curl -L -o NOTICE https://huggingface.co/GSsmart/XGEN-GSsmart-JING/resolve/main/NOTICE
1.39 kB
| XGEN-JING | |
| Copyright 2026 XGEN Team. All rights reserved. | |
| XGEN-JING code and model modifications are released under the MiniMax H3 | |
| Community License Agreement; see LICENSE. | |
| MiniMax H3 is licensed under the MiniMax H3 Community License Agreement, Copyright © 2026 MiniMax. All Rights Reserved. | |
| https://huggingface.co/MiniMaxAI/MiniMax-H3 | |
| This demo uses MiniMax-H3 components from Hugging Face Diffusers. | |
| Selected transformer-forward and attention conventions are adapted from: | |
| https://github.com/huggingface/diffusers/tree/abc5e9bf71fd38f53cd471bc3acaa84bc5ecbfdc | |
| Copyright 2026 The MiniMax and HuggingFace Teams. All rights reserved. | |
| These upstream portions retain their Apache License, Version 2.0; | |
| see LICENSE.apache-2.0. The adaptations add JING controls and inference support. | |
| JING Flash builds upon the FlashGen four-step model published by Beidouqixing: | |
| https://huggingface.co/Beidouqixing/minimax-h3-4step-lora-flashgen | |
| The upstream release is published under Apache-2.0; see LICENSE.apache-2.0. | |
| JING Flash includes model modifications by XGEN Team. The resulting H3 model | |
| derivative is subject to the MiniMax H3 Community License Agreement. | |
| The runtime calls SGLang's public checkpoint and sharded-inference loader: | |
| https://github.com/sgl-project/sglang/tree/95140a7b0c9fc2f87a2a6cf6f6f0df8640a73174 | |
| SGLang is distributed under Apache-2.0. Its source is not vendored here. | |