阿萨德萨达啊打算
楼主，生成的时长只能5秒吗？怎么才能生成10~20秒视频？
Felix0531 发表于 2026-6-22 15:46
楼主，生成的时长只能5秒吗？怎么才能生成10~20秒视频？
更改帧数，5秒大约=81帧
受制于wan2.2模型限制（5秒最佳），不建议生成超过5秒视频，会出现人物一致性崩毁或飘移等问题
这个跟V2版本有什么区别，主推的是v2版本。
ComfyUI 连接成功
* Running on local URL:http://0.0.0.0:7860
* To create a public link, set `share=True` in `launch()`.
got prompt
WARNING: PlaySound.IS_CHANGED() missing 1 required positional argument: 'self'
Using pytorch attention in VAE
Using pytorch attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.float16
gguf qtypes: Q5_K (144), F32 (49), F16 (24), Q6_K (25)
Attempting to recreate sentencepiece tokenizer from GGUF file metadata...
Created tokenizer with vocab size of 256384
Dequantizing token_embd.weight to prevent runtime OOM.
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
Requested to load WanTEModel
loaded completely; 13828.80 MB usable, 5129.20 MB loaded, full load: True
gguf qtypes: F16 (694), Q4_K (280), Q6_K (120), F32 (1)
model weight dtype torch.float16, manual cast: None
model_type FLOW
Global: tokens (99 tokens)
Segment 0: tokens (22 tokens)
Segment 1: tokens (21 tokens)
Segment 2: tokens (17 tokens)
Latent: 21 frames, 1560 tokens/frame, segments:
Requested to load WanVAE
loaded completely; 4918.36 MB usable, 242.03 MB loaded, full load: True
Requested to load WAN21
loaded partially; 8576.95 MB usable, 8534.73 MB loaded, 802.46 MB offloaded, 42.22 MB buffer reserved, lowvram patches: 0
Web extensions folder found at D:\yxrj\ComfyUI_Wan2.2-Remix-V3\ComfyUI\web\extensions\ComfyLiterals
server: v1.3.4 Loaded
web root: D:\yxrj\ComfyUI_Wan2.2-Remix-V3\ComfyUI\custom_nodes\ComfyUI-Easy-Use\web_version/v2 Loaded
ComfyUI found: D:\yxrj\ComfyUI_Wan2.2-Remix-V3\ComfyUI
'D:\yxrj\ComfyUI_Wan2.2-Remix-V3\ComfyUI' added to sys.path
# 😺dzNodes: LayerStyle -> Cannot import name 'guidedFilter' from 'cv2.ximgproc'
A few nodes cannot works properly, while most nodes are not affected. Please REINSTALL package 'opencv-contrib-python'.
For detail refer to https://github.com/chflame163/ComfyUI_LayerStyle/issues/5
Loaded 48 extraordinary nodes. 🎉
0%| | 0/4 Built penalty matrix (video): Lq=32760, Lk=512, nonzero=1684800/16773120
25%|██▌ | 1/4
50%|█████ | 2/4
75%|███████▌| 3/4
100%|██████████| 4/4
100%|██████████| 4/4
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 partially; 8544.96 MB usable, 8502.73 MB loaded, 834.45 MB offloaded, 42.22 MB buffer reserved, lowvram patches: 0
生成超时
songtso8 发表于 2026-7-8 06:43
ComfyUI 连接成功
* Running on local URL:http://0.0.0.0:786 ...
你看comfyui/outputs目录下，应该已经成功了
可以再运行一次
无言以对 发表于 2026-7-8 08:38
你看comfyui/outputs目录下，应该已经成功了
可以再运行一次
comfyui/outputs目录下没有生成的文件
songtso8 发表于 2026-7-9 22:15
comfyui/outputs目录下没有生成的文件
报错后，X掉黑色命令窗口，重新启动运行
还有，你是什么显卡，运存多大
无言以对 发表于 2026-7-10 09:03
报错后，X掉黑色命令窗口，重新启动运行
还有，你是什么显卡，运存多大
...
显卡nvidia quadro p5000 16g显存，32g运行内存
songtso8 发表于 2026-7-10 20:34
显卡nvidia quadro p5000 16g显存，32g运行内存
是不是时长太长了，先用默认参数试试