[GH-ISSUE #167] no response with the gradio page(app_januspro.py) ,but there is no error log #131

New issue

Open

opened 2026-10-26 21:12:46 +00:00 by bsakaguchi · 2 comments

bsakaguchi commented

2026-10-26 21:12:46 +00:00

Owner

Originally created by @Alexhendar on GitHub (Feb 13, 2025).
Original GitHub issue: https://github.com/deepseek-ai/Janus/issues/167

Run the service with command: 【python3 app_januspro.py】

Python version is above 3.10, patching the collections module.
/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/transformers/models/auto/image_processing_auto.py:590: FutureWarning: The image_processor_class argument is deprecated and will be removed in v4.42. Please use slow_image_processor_class, or fast_image_processor_class instead
warnings.warn(
Using a slow image processor as use_fast is unset and a slow processor was saved with this model. use_fast=True will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with use_fast=False.
You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>. This is expected, and simply means that the legacy (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set legacy=False. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message.
Some kwargs in processor config are unused and will not have any effect: ignore_id, mask_prompt, image_tag, num_image_tokens, sft_format, add_special_token.

Running on local URL: http://127.0.0.1:7860

使用python3 app_januspro.py命令启动程序后，访问Gradio页面测试文生图功能，页面一直loading，没有图片生成，没有错误日志，哪位大佬指导一下，感谢了

Originally created by @Alexhendar on GitHub (Feb 13, 2025). Original GitHub issue: https://github.com/deepseek-ai/Janus/issues/167 Run the service with command: 【python3 app_januspro.py】 Python version is above 3.10, patching the collections module. /Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/transformers/models/auto/image_processing_auto.py:590: FutureWarning: The image_processor_class argument is deprecated and will be removed in v4.42. Please use `slow_image_processor_class`, or `fast_image_processor_class` instead warnings.warn( Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`. You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message. Some kwargs in processor config are unused and will not have any effect: ignore_id, mask_prompt, image_tag, num_image_tokens, sft_format, add_special_token. * Running on local URL: http://127.0.0.1:7860 <img width="1771" alt="Image" src="https://github.com/user-attachments/assets/609eb9fa-ebc3-487d-a302-7b7a3b034c61" /> --------------------------------- 使用python3 app_januspro.py命令启动程序后，访问Gradio页面测试文生图功能，页面一直loading，没有图片生成，没有错误日志，哪位大佬指导一下，感谢了

bsakaguchi commented

2026-10-26 21:12:49 +00:00

Author

Owner

@packyzhou commented on GitHub (Feb 17, 2025):

我也一样，看后台报错信息好像是代码错了，报输入模型参数跟代码参数类型不一致导致

@packyzhou commented on GitHub (Feb 17, 2025): 我也一样，看后台报错信息好像是代码错了，报输入模型参数跟代码参数类型不一致导致

bsakaguchi commented

2026-10-26 21:12:49 +00:00

Author

Owner

@Latentnaut commented on GitHub (Feb 20, 2025):

I'm in ComfyUI and got this:

Loading model from: C:\AI\ComfyUI_windows_portable\ComfyUI\models\Janus-Pro
Some kwargs in processor config are unused and will not have any effect: sft_format, ignore_id, mask_prompt, num_image_tokens, image_tag, add_special_token.

@Latentnaut commented on GitHub (Feb 20, 2025): I'm in ComfyUI and got this: Loading model from: C:\AI\ComfyUI_windows_portable\ComfyUI\models\Janus-Pro Some kwargs in processor config are unused and will not have any effect: sft_format, ignore_id, mask_prompt, num_image_tokens, image_tag, add_special_token.

No labels

pull-request

No milestone

No project

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#131

No description provided.

Rows
Columns