-
Notifications
You must be signed in to change notification settings - Fork 201
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How about using lora to do video style changes?please enlighten me #39
Comments
Thank you for your reply. May I ask if you have used xformer to speed up reasoning? I have noticed that the speed of this excellent work seems to be a bit slow. Or do you have any other ways to speed up reasoning? |
We didn't tested our code with xformer to speed up. |
And we are implementing our method in Diffusers, which might be more efficient. |
Thank you for your reply.Looking forward to your further work! |
大佬,请问如何基于 embedding 进行风格化呢,有相关的融合示例吗 |
是text embedding吗? 我没用过,所以具体细节我也不清楚。 |
https://civitai.com/models/9416?modelVersionId=11173 我看到这个风格很强,所以想测试一下 ,他不可以像Lora 一样融合到模型里吗,我下载的embedding **.pt 应该放到哪里,如何才能加载到代码里 |
这种看上去是用的直接把text embedding用到base model (base model可以加上其他LoRA)上了。 |
基础模型就是原版的stable diffusion 1.5模型+controlnet( 这部分具体代码是controlnet里的,其中对应LatentDiffusion 类的应该是,具体需要你研究一下controlnet的代码 |
当我增加embedding 模型加载,出现没有属性error,我对比 embedding 源码 和 controlnet 代码里面的ddpm,发现少一部分 embedding 相关代码,我不确定是 diffusion 版本问题还是 embedding 源码特有的 |
self.control_model 是 controlnet,是stable diffusion的旁路 self.model.diffusion_model 才是 stable diffusion 本体,才是LatentDiffusion model |
我看了一下,你的是texture inversion的代码,是基于LDM修改的代码, 但这已经超出了我这个项目的范围,所以后面我就不再继续解答相关问题,这个issue也已经讨论和lora无关的问题很久了。 |
好的,我在查一下其他相关实现代码,看看有没有解决办法,谢谢您的解答 |
@zhanghongyong123456 had any luck with it? |
No description provided.
The text was updated successfully, but these errors were encountered: