Qwen-Image-2.1-Lightning-v2-RL

Use it to generate images from prompts or create and edit images using one or more reference images.

Availability

Model weights and inference instructions are on Hugging Face.

Pricing model

Not established

Deployment

Load the weights with Diffusers for inference.

Privacy

Not established

Licence

Qwen Research License, including non-commercial terms.

• Supports text-to-image generation, single-reference image editing, and multi-reference image generation. ^[1]

  It supports text-to-image generation, single-reference image editing, and multi-reference image generation with **4 denoising steps** and **CFG = 1.0**.

• Uses four denoising steps and CFG = 1.0. ^[1]

  It supports text-to-image generation, single-reference image editing, and multi-reference image generation with **4 denoising steps** and **CFG = 1.0**.

• The release provides full transformer weights in a safetensors file and an inference configuration. ^[1]

  The release provides the **full transformer weights** in a single `diffusion_pytorch_model.safetensors` file, together with `config.json`.

• The example loads the model with Diffusers and runs it on CUDA. ^[1]
• The model is derived from Qwen-Image-2.1 and is subject to the Qwen Research License, including non-commercial terms. ^[1]

  This model is derived from Qwen-Image-2.1 and is subject to the [Qwen Research License](https://huggingface.co/Qwen/Qwen-Image-2.1/blob/main/LICENSE), including its non-commercial terms.