Image Resolution Support in Janus Models

[zzzyzh]

Hi,

I noticed that the example provided generates images with a resolution of 384. When I try to directly change it to 1024, I encounter an error.

Could you clarify whether the Janus series models only support a single output resolution? If 1024x1024 resolution is supported, how should I modify the parameters to generate images at that resolution?

Thanks in advance for your help!

[KwangryeolPark]

According to official paper, https://github.com/deepseek-ai/Janus/blob/main/janus_pro_tech_report.pdf, the model does not support the other resolutions except for 384x384.

3.4. Qualitative Results
We present results on multimodal understanding in Figure 4. Janus-Pro exhibits impressive
comprehension abilities when handling inputs from various contexts, showcasing its powerful
capabilities. We also present some text-to-image generation results in the lower part of Figure 4.
The images generated by Janus-Pro-7B are highly realistic, and despite having a resolution of
only 384 × 384, they still contain a lot of details. For imaginative and creative scenes, Janus-Pro7B accurately captures the semantic information from the prompts, producing well-reasoned
and coherent images.