Instructions to use chenguolin/sv3d-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use chenguolin/sv3d-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("chenguolin/sv3d-diffusers", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Hello 您能分享模型引用的代码文件么?
#1
by amerssun - opened
我发现您的model_index.json里面放了自定义的结构,extensions.mvdiffusion.models.unets.unet_spatio_temporal_condition。您可以分享它的相关代码么?另外,不确定您的模型版本是SV3D_U还是SV3D_P,您可以提供更详细的描述么
你好,模型版本是SV3D_P。因为是自己使用的,所有没有完善文档。你可以自己修改diffusers库中的UNetSpatioTemporalConditionModel类,我记得改动不大,让它能处理camera_embedding就可以。可能之后有时间会整理一下sv3d-diffusers。
hello 我按照您说的方法改了一下,但视频出现了奇怪的扭曲,可能是我pipeline或者unet脚本中某些细节有问题。。。不知道您什么时候有意向整理一份开源代码,期待中
chenguolin changed discussion status to closed
非常感谢~ 很抱歉现在才看到您的消息,但这对我还是有很大帮助~非常感谢~~~