import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("samuelchristlie/Lance-GGUF", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0] _ _______
| | __ _ _ _ __ ___ __|__ / _ )
| |__/ _` | ' \/ _/ -_)___|_ \ _ \
|____\__,_|_||_\__\___| |___/___/
Lance-GGUF
Direct GGUF Conversion of bytedance-research/Lance
Lance is a lightweight native unified multimodal model that supports image and video understanding, generation, and editing within a single framework. With only 3B active parameters, it delivers strong performance across image generation, image editing, video generation, and video understanding benchmarks — trained entirely from scratch.
Table of Contents 📝
- ▶ Usage
- 📃 License
- 🙏 Acknowledgements
▶ Usage
Download models using huggingface-cli:
pip install "huggingface_hub[cli]"
huggingface-cli download samuelchristlie/Lance-GGUF --local-dir ./Lance-GGUF
You can also download directly from this page.
📃 License
This model is a derivative work of the original model licensed under the Apache 2.0 License, and is therefore distributed under the terms of the same license.
🙏 Acknowledgements
Thanks to Patrick Gillespie for creating the ASCII text art tool used in this project https://patorjk.com/software/taag/
ByteDance Research for the Lance model https://huggingface.co/bytedance-research/Lance
- Downloads last month
- 3,349
4-bit
5-bit
6-bit
8-bit
16-bit