ComfyUI-CogVideoX-MZ

ComfyUI-CogVideoX-MZ copied to clipboard

Got an error reported at CogVideoSampler `# ComfyUI Error Report ## Error Details - **Node Type:** CogVideoSampler - **Exception Type:** TypeError - **Exception Message:** CogVideoXPipeline.__call__() got an unexpected keyword argument...

gengzhichen

Cannot generate a cpu tensor from a generator of type cuda.

1

I get the following error on my ROCM install with an AMD 6900 XT. Im guessing this isnt supported on ROCM?

GoDJr

OOM

7

你好，我使用786X1024的图片作为底图，使用“workflow_FUN_I2V_GGUF_Q4_0.png”这个工作流，生成1024分辨率的视频会爆显存；768分辨率下没问题。 显卡：RTX 4060TI 16GB. OS: Ubuntu22.04 Docker 中运行 vae encode tiling 已经打开 是不是因为我的底图太大了？

littleloulou

A new error was found. Please take a look.

1

CogVideoXFunSampler CogVideoX_Fun_Pipeline_Inpaint.__call__() got an unexpected keyword argument 'noise_aug_strength'

michael007777

Given groups=1, weight of size [3072, 16, 2, 2], expected input[26, 32, 60, 90] to have 16 channels, but got 32 channels instead

4

got prompt Encoded latents shape: torch.Size([1, 1, 16, 60, 90]) Temporal tiling disabled 0%| | 0/50 [00:00

jackkite

Trying to convert Float8_e4m3fn to the MPS backend but it does not have support for that dtype.

8

换了各种weight_type都不行。

ZeeMenng

emerging issue

6

zhjf3888

weight_dtype as GGUF?

1

How can I set the weight_dtype as GGFU? Because it doesn't appeared in the list. 

clemarjonlaguardia

Add pyproject.toml for Custom Node Registry

1

Hey! My name is Robin and I'm from [comfy-org](https://comfy.org/)! We would love to have you join the Comfy Registry, a public collection of custom nodes which lets authors publish nodes...

robinjhuang

MZ_CogVideoXLoader not found

3

 Using this workflow. [CogVideoMZ-basic.json](https://github.com/user-attachments/files/17083889/CogVideoMZ-basic.json)

ZeroCool22