CogVideo

CogVideo copied to clipboard

About Frame Pack & 3d Rope

4

### Feature request / 功能建议 Thanks for your work! The paper mentioned `Frame Pack`, which requires to generate attention masks (https://arxiv.org/abs/2307.06304), the `forward` function : `kwargs["input_ids"] = kwargs["position_ids"] = kwargs["attention_mask"]...

burnquiet

Mac max1 14.6 64g内存 跑CogVideoX-2btest.py报错

1

### System Info / 系統信息 Mac max1 14.6 64g内存跑这个代码 import torch from diffusers import CogVideoXPipeline from diffusers.utils import export_to_video prompt = "A panda, dressed in a small, red jacket and...

chaisheng886

NPU out of memory

1

我在昇腾910B上部署完成，python inference/cli_demo.py 时报错： `hidden_states = F.scaled_dot_product_attention( RuntimeError: NPU out of memory. Tried to allocate 35.31 GiB (NPU 0; 60.97 GiB total capacity; 26.13 GiB already allocated; 26.13 GiB current active;...

fallbernana123456

CUDA OOM and possible solution -- diffusers cli_demo.py with Nvidia 3090 24GB

23

### System Info / 系統信息 Thanks very much for releasing this great work! In case this helps anyone else: The diffusers `cli_demo.py` raised the CUDA OOM error below on an...

cktlco

docs: add Japanese README

2

I created Japanese translated README.

eltociear

What optimizer is used to replace the FusedEmaAdam on the NPU device?

2

### System Info / 系統信息 I am trying to sft on NPU device. However, the FusedEmaAdam relies on cuda, which is not available on NPU device. So, what optimizer is...

NickPan7779

Update README_zh.md

1

更新 文档错误

icowan

[Q] Is it possible to generate portrait videos i.e 480x720 instead of 720x480p out of the box

3

If no, how to do it?

rozeappletree

### System Info / 系統信息 - Python: 3.8.19 - Diffusers: 0.30.0 - OS: centos:7 - NVIDIA Driver: 550.54.15 - CUDA: 12.4 - NVIDIA GPU: NVIDIA L40 - NVIDIA GPU Memory:...

CodeLyokoscj

Great work! when are you planning to release image-to-video models?

11

gxd1994