tayton42

关于视频编解码硬件加速的问题

1

#159 我遇到了和该问题一致的情况，在使用v100时，模型推理速度只有2-3帧，speedtest却有60-70帧，请问是以下代码造成这种问题吗 ``` if output_foreground is not None: writer_fgr.write(fgr[0]) if output_alpha is not None: writer_pha.write(pha[0]) # pha[0] [12,1,h,w] if output_composition is not None: if output_type == 'video': com = fgr...

请问该数据集的格式是什么，只是全部由背景图片构成吗，是否存在任何标记，另外，有推荐的公开数据集吗

About Distributed Training

3

Thank you for your research.I have a question about single multi-card training, when my code starts to ` self.model_ddp = DDP(self.model, device_ids=[self.rank], broadcast_buffers=False, find_unused_parameters=True)` Processes on other GPUs appear on...

Hi, I noticed that in some scenes there is a large area of translucent vignetting, I think this is entirely due to the GRU, is it possible to mitigate this...

Hi!I don't quite understand the num_frames parameter in the video, does it have anything to do with multiple prompts, does the video support multiple prompts?Thanks

Thanks for the data, I am using a dataset like DAVIS structure for the first time, I want to turn the dataset into a human segmented dataset, is there any...

Thank you for the code you submitted. Can you provide the predicted pose file for reference? Thank you!

如题，没有找到lq_enhancer...

Issues regarding the compatibility of flux lora

4

Thank you very much for sharing the eligen lora at https://www.modelscope.cn/models/DiffSynth-Studio/Eligen, but I encountered a dict mismatch issue when trying to apply it to the original flux https://github.com/black-forest-labs/flux/blob/main/src/flux/model.py. How can...