必须赞一个，楼主不要停止你的才华，我作为小白在ai上吃过你所说的亏，想不到在这里遇到这样的干货，还是很感动的，希望大神继续努力。
请问大佬我用comfyui跑图每跑一次就会增加硬盘内存过了几天后又会减少这是为什么？
话说有模型分享吗，直接打包挂论坛卖就行，或者卖弄好的ui包这样
6g显卡无缘了
大佬 最近N卡太坑了 请问A卡有可能么
Gaslight001314 发表于 2025-11-10 22:44
这个我没太试过。。我现在在研究二次元涩图为主，暂时还没接触过换脸，但是如果是comfyUI的话，有一个rea ...
有人看有人看！大佬牛批
看来又要出血了，N卡内存太小了跑不了了
CUDA 错误：设备上无法执行内核镜像，有大哥知道这是怎么回事吗
大家伙都是为了满足自己的那一点嗜好才弄AI的吗？有没有学了Comfy UI当作生产力的，出来分享一下心得？
Ninpoi19 发表于 2025-11-10 22:23
哥们，在涩情论坛教comfyui，你是真正滴英雄。话说换脸本地模型有什么好推荐的吗？现在还是insawp fp16（忘 ...
本地换脸试试facefusion，效果差点，胜在简单
我就说老王是学习网站吧
我最近学SD呢，听说SD比COMFYUI简单些，所以从简单的开始
大佬我为什么用cup.bat打开后，控制台加载一会就提示按任意键继续然后不跳网站，用CPU.bat打开后一下子就进网站了，这是什么原因啊大佬
大佬为什么我双击gup控制台加载完之后就提示我按任意键继续，按完之后也没有跳网站，而我用cup跑就一下进网站了
大佬，可以分享一下工作流吗，我刚买回5070ti想试试
连接主机...
连接主机成功
Welcome to Ubuntu 22.04.5 LTS (GNU/Linux 6.6.87.2-microsoft-standard-WSL2 x86_64)
• Documentation:https://help.ubuntu.com
• Management: https://landscape.canonical.com
• Support: https://ubuntu.com/pro
This system has been minimized by removing packages and content that are
not required on a system that users do not log into.
To restore this content, you can run the 'unminimize' command.
Last login: Fri Dec 12 02:25:44 2025 from 172.18.0.1
(diffusion-pipe) root@1d615dc8ebd0:~# deepspeed --num_gpus=1 diffusion-pipe/train.py --deepspeed --config diffusion-pipe/examples/main_FLUX.1-dev.toml
Setting ds_accelerator to cuda (auto detect)
Unable to find hostfile, will proceed with training with local resources only.
cmd = /root/miniconda3/envs/diffusion-pipe/bin/python3.12 -u -m deepspeed.launcher.launch --world_info=eyJsb2NhbGhvc3QiOiBbMF19 --master_addr=127.0.0.1 --master_port=29500 --enable_each_rank_log=None diffusion-pipe/train.py --deepspeed --config diffusion-pipe/examples/main_FLUX.1-dev.toml
Setting ds_accelerator to cuda (auto detect)
WORLD INFO DICT: {'localhost': }
nnodes=1, num_local_procs=1, node_rank=0
global_rank_mapping=defaultdict(<class 'list'>, {'localhost': })
dist_world_size=1
Setting CUDA_VISIBLE_DEVICES=0
process 35732 spawned with command: ['/root/miniconda3/envs/diffusion-pipe/bin/python3.12', '-u', 'diffusion-pipe/train.py', '--local_rank=0', '--deepspeed', '--config', 'diffusion-pipe/examples/main_FLUX.1-dev.toml']
Setting ds_accelerator to cuda (auto detect)
cdb=None
Initializing TorchBackend in DeepSpeed with backend nccl
: Traceback (most recent call last):
: File "/root/diffusion-pipe/train.py", line 303, in <module>
: model = flux.FluxPipeline(config)
: ^^^^^^^^^^^^^^^^^^^^^^^^^
: File "/root/diffusion-pipe/models/flux.py", line 183, in __init__
: transformer = diffusers.FluxTransformer2DModel.from_pretrained(
: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
: File "/root/miniconda3/envs/diffusion-pipe/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
: return fn(*args, **kwargs)
: ^^^^^^^^^^^^^^^^^^^
: File "/root/miniconda3/envs/diffusion-pipe/lib/python3.12/site-packages/diffusers/models/modeling_utils.py", line 1179, in from_pretrained
: resolved_model_file, sharded_metadata = _get_checkpoint_shard_files(
: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
: File "/root/miniconda3/envs/diffusion-pipe/lib/python3.12/site-packages/diffusers/utils/hub_utils.py", line 393, in _get_checkpoint_shard_files
: raise FileNotFoundError(
: FileNotFoundError: /root/diffusion/models/FLUX.1-dev/transformer/ does not appear to have a file named /root/diffusion/models/FLUX.1-dev/transformer/diffusion_pytorch_model-00001-of-00003.safetensors which is required according to the checkpoint index.
: Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
Killing subprocess 35732
['/root/miniconda3/envs/diffusion-pipe/bin/python3.12', '-u', 'diffusion-pipe/train.py', '--local_rank=0', '--deepspeed', '--config', 'diffusion-pipe/examples/main_FLUX.1-dev.toml'] exits with return code = 1
a卡和i卡跑图大概也没问题，我用b580搞过本地跑图和本地翻译漫画都还好（b站都有教的，comf和sd都有整合包。sakura有i卡支持
就是没有方便的n卡一键安装包，一些插件支持的也不好
楼主下次发帖的时候加个收费附件就可以收到积分了，附件里面随便放个东西，愿意给的自己买就行了
瞬间上手，可能因为我有开发基础，大佬牛逼
大佬，可以+WX或者QQ聊一聊这方面的技术吗？