deepseek-ai/Janus
1
0
Fork 0
mirror of https://github.com/deepseek-ai/Janus.git synced 2026-11-05 00:57:18 +00:00
Code Issues 183 Projects Packages Wiki Activity

[GH-ISSUE #104] Image Resolution Support in Janus Models #80

New issue
Open
opened 2026-10-26 21:11:44 +00:00 by bsakaguchi · 1 comment
bsakaguchi commented 2026-10-26 21:11:44 +00:00
Owner
Copy link

Originally created by @zzzyzh on GitHub (Jan 30, 2025).
Original GitHub issue: https://github.com/deepseek-ai/Janus/issues/104

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!

Originally created by @zzzyzh on GitHub (Jan 30, 2025). Original GitHub issue: https://github.com/deepseek-ai/Janus/issues/104 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!
bsakaguchi commented 2026-10-26 21:11:46 +00:00
Author
Owner
Copy link

@KwangryeolPark commented on GitHub (Jan 30, 2025):

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.

<!-- gh-comment-id:2624372349 --> @KwangryeolPark commented on GitHub (Jan 30, 2025): 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.
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/Janus#80
No description provided.