Sze-qq

Results 9 comments of Sze-qq

[FEATURE]: example - stylegan_xl

Hi 请问你有兴趣和我们一起做一个stylegan-XL的例子吗？或许可以一起讨论一下呢 :D

[FEATURE]: Integrate StableDiffusion Dreambooth with ColossalAI

Hi, thanks for reaching out! I think it’s pretty awesome. Can I check it with our team and get back to you ASAP?

[BUG]: after finetuning dreambooth, infer with trained model.

Hi, thanks for reaching out! We'll reproduce your bug and get back to you ASAP. :)

[BUG]: FusedScaleMaskSoftmax last dimension does not sum to 1

Thanks for your issue. We'd get back to you ASAP. :)

PixArt Sigma

Hey ShawnFumo, thank you very much for your suggestion. We will definitely look into it!

the generated video quality different with the samples shown in gallery

Sure. Here are the parameters we used to generate the video: Resolution: 720p Sampling Steps: 100 Aesthetic Score: 7 Refine Prompt with GPT-4: Unchecked Other settings: Default Prompt: A Japanese...

the generated video quality different with the samples shown in gallery

Hi @runzeer . I generated the image first and then clicked "Generate Video" on Gradio. Hope this helps.

请问能否写清楚如何利用自己的输入做模型推理，没看明白doc

谢谢您的建议，我们稍后更新一下ReadMe :)

train problem

Hey, xinyuxiao. May I inquire about the computing resources you are utilizing for running the tasks?