最强图生视频FramePack中文一体包，6G显存可玩

温莎公爵

l7841902 发表于 2025-4-22 22:54
可灵这么强吗

可灵很牛，个人觉得秒杀其它一切国内外竞品，唯一的缺点就是太贵，除了公司、富哥、有稳定变现的自媒体人，普通玩家根本不用考虑它，用不起的。

qqcxcz

建议把随机种子和执行次数加上，不然抽卡跑太慢不能一直等着

x777

厉害的，谢谢分享。。

4dashuaige

2080TI22G.生成PNG图片。没有视频

av203

感谢滚石大大

wosildj

谢谢分享！！！！！！！

axin709

请问大佬，可以用cpu吗，A卡行不行

比昂

msshbah 发表于 2025-4-21 19:12
大佬，请问这个怎么解决

关掉梯子

小蛋筒

torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 28.86 GiB. GPU 0 has a total capacity of 22.00 GiB of which 17.49 GiB is free. Of the allocated memory 2.78 GiB is allocated by PyTorch, and 513.92 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/ ... vironment-variables)
Unloaded DynamicSwap_LlamaModel as complete.
Unloaded CLIPTextModel as complete.
Unloaded SiglipVisionModel as complete.
Unloaded AutoencoderKLHunyuanVideo as complete.
Unloaded DynamicSwap_HunyuanVideoTransformer3DModelPacked as complete.


2080TI 22G的也没办法用吗？

小蛋筒

torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 28.86 GiB. GPU 0 has a total capacity of 22.00 GiB of which 17.49 GiB is free. Of the allocated memory 2.78 GiB is allocated by PyTorch, and 513.92 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/ ... vironment-variables)
Unloaded DynamicSwap_LlamaModel as complete.
Unloaded CLIPTextModel as complete.
Unloaded SiglipVisionModel as complete.
Unloaded AutoencoderKLHunyuanVideo as complete.
Unloaded DynamicSwap_HunyuanVideoTransformer3DModelPacked as complete.


貌似2080TI 22G的都用不了