TkskKurumi

**Description** Hi, experts. Thanks a lot for your amazing works I'm training Textual-Inversion embdding in "Train" tag. The embedding is named `pseudo_token_1`. When I pause the training by pressing \^C...

ImagePaint unexcpectedly resizes image half automatically when used as output.

1

### Describe the bug Hi experts, When I use an Image component as image uploading and sync (tested both with Image.upload or Button.submit) its image to an ImagePaint component, the...

in train_util.py `# determine SD or Diffusers`. Maybe because my ckpt is a symbolic link to save disk usage. So that `path.isfile` returns False, then causing from_pretrained("XXX.ckpt") throw errors. Maybe...

我看到尽管```QwenImagePipeline.__call__```有把tiled, tile_size, tile_stride参数传入self.vae.decode，但```QwenImageVAE.decode```只是用**kwargs接收，并没有实际用到。 https://github.com/modelscope/DiffSynth-Studio/blob/afd101f3452c9ecae0c87b79adfa2e22d65ffdc3/diffsynth/pipelines/qwen_image.py#L444 https://github.com/modelscope/DiffSynth-Studio/blob/afd101f3452c9ecae0c87b79adfa2e22d65ffdc3/diffsynth/models/qwen_image_vae.py#L716 我对模型原理了解有限，想请教一下：请问是 功能暂未实现 还是 QwenImageVAE模型架构本身就无法支持tiled decoding？感谢您的时间和贡献！

[Feature] Work as an HTTP service.

3

### Feature Summary Work as an HTTP service. ### Detailed Description Thanks for building this project, this is a fast and clean implementation. I'd like to suggest adding a server...