AI is happening. The future is updating.qwen-360-diffusion
Qwen 360 Diffusion is a rank 128 LoRA built on top of a 20B parameter MMDiT (Multimodal Diffusion Transformer) model, designed to generate 360 degree equirectangular projection images from text descriptions. The model was trained from the Qwen Image model on an extremely diverse dataset composed of tens of thousands of equirectangular images, depicting landscapes, interiors, humans, animals, and objects. All images were resized to 2048x1024 before training. The model was also trained with a diverse dataset of normal photos for regularization, making the model a realism finetune when prompted correctly.
Qwen 360 Diffusion is a rank 128 LoRA built on top of a 20B parameter MMDiT (Multimodal Diffusion Transformer) model, designed to generate 360 degree equirectangular projection images from text descriptions. The model was trained from the Qwen Image model on an extremely diverse dataset composed of tens of thousands of equirectangular images, depicting landscapes, interiors, humans, animals, and objects. All images were resized to 2048x1024 before training. The model was also trained with a diverse dataset of normal photos for regularization, making the model a realism finetune when prompted correctly.