Instructions to use lightx2v/Qwen-Image-Lightning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Qwen-Image-Lightning with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("lightx2v/Qwen-Image-Lightning") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Request to Build a Qwen‑Image‑Lightning‑Style Model Based on Skywork‑UniPic
#3
by PlayAI - opened
Hi @lightx2v – Skywork just released Skywork-UniPic (MIT), a 1.5‑B‑parameter unified autoregressive model that seamlessly handles image understanding, text‑to‑image generation, and image editing; I’d love for you to create a model similar to this Qwen‑Image‑Lightning model. The model weights are available at https://huggingface.co/Skywork/Skywork-UniPic-1.5B and the code at https://github.com/SkyworkAI/UniPic—could you create a lightning model so users can easily create on the Skywork-UniPic model? Thank you!