Repository Issue Activity (beta)

#237 GenEval Score Janus-Pro 1B

#239 Cannot reproduce Janus-Pro-1B understanding benchmark results with VLMEvalKit

#86 comparison with flux?

#238 DeepSeek4V多模态刚上线就翻车？zw-mtt独家解读 DeepSeek4V Multimodal just went live and crashed? Exclusive interpretation of ZW MTT

#235 Woman

#229 A mystical white deer in moonlit forest, ethereal glow, magical atmosphere, detailed fur, 4K resolution 1024×768像素

#47 AMD support

#123 Janus Pro-7B在带有图片的few-shot中会导致输出乱码

#226 requirements break nunchaku

#213 可以使用摩尔线程的mtt s80进行部署吗？

#227 Generating images with img_size=512

#194 发现基本的OCR的功能都很多问题，咋能更好理解图片呢

#225 Question on Improving Image Quality 关于提升生成图像质量的请教

#224 Use_webapi

#223 calling the api

#221 Does Janus' image generation mode support multi-modal input?

#200 华为的910a卡，支持Janus模型吗？

#222 In the example provided in the code, the image generation function only supports text input. Can the image generation support multimodal input? How should image input be handled?

#195 How to batch process如何批量处理？

#165 Unofficial Training Code sample.

#214 No module named 'janus

#35 Typo in your report

#220 当前项目 requirements.txt 的依赖声明无法运行模型，希望能尽快更新依赖说明

#209 可以像OpenAI一样对图像做吉卜力风格的转换吗？

#171 Add an option to disable flash attention for older GPU's