-
Notifications
You must be signed in to change notification settings - Fork 133
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
新增模型Hotshot-XL #411
Comments
Hotshot-XL 版本要求是 diffusers==0.21.4,ppdiffusers develop分支是0.19.4,那是要用upgrade_ppdiffusers0240分支ppdiffusers吗 |
是的 目前先基于upgrade_ppdiffusers0240开发 ppdiffusers0.24.0会在最近一两周发版 |
模型文件较大 14G,是不是能转为paddle格式下载使用,text_encoder和tokenizer转换规则和stable diffusion类似,hsxl_temporal_layers 如果转换规则不同可以本地再修改 |
可以呀 你那边可以转吗 我帮你上传到bos |
模型文件 https://huggingface.co/co63oc/hotshotxl/tree/main/ 文件MD5
PR #449 |
模型已上传bos,id为co63oc/hotshotxl |
https://bj.bcebos.com/paddlenlp/models/community/co63oc/hotshotxl/controlnet_depth/config.json 但是这个存在 如果要拆分为单独的模型库也可以拆,现在就是在测试 |
@CrazyBoyM 帮忙重新上传一下吧 |
好的可以下载了 |
#411 推理 paddle ![pd_output](https://github.com/PaddlePaddle/PaddleMIX/assets/4617245/10f569e5-322f-48c2-898e-5937bb67f4f6) torch ![pt_output](https://github.com/PaddlePaddle/PaddleMIX/assets/4617245/f7d61f02-4fb0-46ac-ac2c-c1220da2fb79) controlnet_depth paddle ![pd_output](https://github.com/PaddlePaddle/PaddleMIX/assets/4617245/c1f83b79-5fed-4397-92ae-383503de669b) torch ![pt_output](https://github.com/PaddlePaddle/PaddleMIX/assets/4617245/4e3c0379-8d72-46fd-8bb2-cd87480b97cf) controlnet_canny paddle ![pd_output](https://github.com/PaddlePaddle/PaddleMIX/assets/4617245/c5c1fa93-31ac-4a50-8ab4-727c18992674) torch ![pt_output_422](https://github.com/PaddlePaddle/PaddleMIX/assets/4617245/97e55f08-716e-4f08-96d1-57aeab369ca7) 原仓库运行需要修改 torch.Generator(device) ,设置随机数设备为 gpu 设备 微调训练使用V100 32G显示显存不足,暂时没有合适硬件测试
新增模型Hotshot-XL
任务描述
任务背景
完成步骤
参考PR:#401
提交内容:
The text was updated successfully, but these errors were encountered: