-
Hi, thanks for the work! I'm trying to train the u-vit part from the original u-vit codebase, but I'm having difficulty modifying it to fit the rest of the unidiffuser framework. What loss/model confi…
-
我在训练的时候，accelerate报错gpu_ids找不到
Traceback (most recent call last):
File "/opt/anaconda3/envs/UVIT/bin/accelerate", line 8, in
sys.exit(main())
File "/opt/anaconda3/envs/UVIT/lib/python3.8/…
-
Which file is the U-VIT code in? Can you tell me?
-
I would be extremely grateful.
-
``@baofff
你好，我按照readme的说明训练，但是发生错误：
subprocess.CalledProcessError: Command '['torchrun', '--nproc_per_node', '2', 'train.py', '--config=configs/celeba64_uvit_small.py']' returned non-zero exit stat…
-
Hello,I am very interested in your work on camodiffusion, but I have been confused about your code for a while. In your file train.py, you instantiate three objects called cond_uvit,model, and diffusi…
-
Great work. Does unidiffuser need to use gpt2(llm) for training? And at what stage should the llm be fine-tuned?
-
I met a problem when training on my single RTX 4090. The predicted target occurs some black sub-images when training after 36k steps. The learning rate is set to 5e-5 and batch size is 64.
Can you gi…
-
GPT2Tokenizer.from_pretrained('gpt2'),can' t load tokenizer for 'gpt2'
-
用的是刘悦大佬的安装包，依赖什么安装提示都正常，模型下载好像也没有问题，运行会自动下载DiT_seed_v2_uvit_whisper_small_wavenet_bigvgan_pruned.pth这个模型，模型下载完成以后在运行提示这个错误
![有道截屏翻译结果_1730079259531](https://github.com/user-attachments/assets/4ecef90…