第六十五篇-ComfyUI+V100-32G+运行Wan2.2-图生视频-GGUF

环境

复制代码

系统：CentOS-7
CPU : E5-2680V4 14核28线程
内存：DDR4 2133 32G * 2
显卡：Tesla V100-32G【PG503】 (水冷)
驱动: 535
CUDA: 12.2
ComfyUI version: 0.4.0
ComfyUI frontend version: 1.34.8

系统软件信息

复制代码

系统信息
OS
linux
Python Version
3.12.12 | packaged by Anaconda, Inc. | (main, Oct 21 2025, 20:16:04) [GCC 11.2.0]
Embedded Python
false
Pytorch Version
2.9.1+cu128
Arguments
main.py --listen --port 8188 --cuda-malloc --lowvram
RAM Total
62.68 GB
RAM Free
60.25 GB

下载模型

https://hf-mirror.com/QuantStack/Wan2.2-I2V-A14B-GGUF/blob/main/HighNoise/Wan2.2-I2V-A14B-HighNoise-Q4_K_M.gguf

https://hf-mirror.com/QuantStack/Wan2.2-I2V-A14B-GGUF/blob/main/HighNoise/Wan2.2-I2V-A14B-LowNoise-Q4_K_M.gguf

https://hf-mirror.com/QuantStack/Wan2.2-I2V-A14B-GGUF/blob/main/VAE/Wan2.1_VAE.safetensors
Wan2.2-I2V-A14B-HighNoise-Q4_K_M.gguf ==> 自己的ComfyUI/models/unet

Wan2.2-I2V-A14B-LowNoise-Q4_K_M.gguf ==> 自己的ComfyUI/models/unet

Wan2.1_VAE.safetensors ==> 自己的ComfyUI/models/vae

启动

bash 复制代码

python main.py --listen --port 8188 --cuda-malloc --lowvram

工作流文件模版

配置参数

运行数据

视频尺寸调整 720*1280

GPU

bash 复制代码

Fri Dec 19 22:29:42 2025
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.129.03             Driver Version: 535.129.03   CUDA Version: 12.2     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  Tesla PG503-216                On  | 00000000:04:00.0 Off |                    0 |
| N/A   42C    P0             269W / 250W |  17776MiB / 32768MiB |     97%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

时间

bash 复制代码

[ComfyUI-Manager] All startup tasks have been completed.
100%|████████████████████████████████████████████████████████████████████████████| 2/2 [07:31<00:00, 225.55s/it]
gguf qtypes: F16 (694), Q4_K (280), Q6_K (120), F32 (1)
model weight dtype torch.float16, manual cast: None
model_type FLOW
Requested to load WAN21
loaded completely; 17787.26 MB usable, 9337.19 MB loaded, full load: True
100%|████████████████████████████████████████████████████████████████████████████| 2/2 [07:30<00:00, 225.13s/it]
Requested to load WanVAE
loaded completely; 10214.01 MB usable, 242.03 MB loaded, full load: True
Prompt executed in 00:16:09

效果

动态的5秒视频

总结

复制代码

	V100-32G Wan2.2 gguf 生成1280*720的5秒视频用时16分钟，最大17G显存
GGUF效果一般,显存降低了，但是生成时长没有变化。后面再试试。