zhuruishu
/

ViewMask-1-to-3

feature-extraction

discrete-diffusion

Model card Files Files and versions

ViewMask-1-to-3

Model checkpoint for Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models, including BF16 weights and the matching text tokenizer.

For code, setup, training, inference, and evaluation, please refer to the official GitHub repository.

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

BF16

·

Paper for zhuruishu/ViewMask-1-to-3

ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models

Paper • 2512.14099 • Published Jun 3