SeeSR

SeeSR copied to clipboard

Load pretrain controlnet error

1

hi, I am training my own model, I want to load pretrain controlnet use "--controlnet_model_name_or_path", but there is an error: Traceback (most recent call last): File "train_seesr.py", line 1000, in...

rainsoulsrx

OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory

2

`OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory C:/SeeSR-main/preset/models/stable-diffusion-2-base.`

AIisCool

The checkpoints can not load

2

Hello! Your work is excellent! In the process of replicating the experiment, I loaded the pre-training file on google drive, but the loading failed, I want to know how to...

Explore008

Thank you for your great work. When I tried to reproduce your code with multiple GPUs, I encountered the problem: 'Duplicate GPU detected: rank 2 and rank 0 both on...

longfafffa

Training time and the total number of used datasset

5

你好，最近在复现本工作，有以下几个问题想请教一下 1.请问使用论文中所述的8 NVIDIA Tesla 32G-V100 GPUs总共需要多久的训练时间？ 2.论文中说batchsize设置为192，iter为150K，那么train_batch_size和gradient_accumulation_steps这两个参数应该如何设置？我的理解是train_batch_size*gradient_accumulation_steps*GPU数量=192，不知道是否正确。另外arxiv上v1版本batchsize为32，v2为192，差异很大，这两个指的是总batchsize还是每张卡的batchsize，应该以哪个为准。 3.请问训练所使用的数据集裁剪之后总共包含多少图像？对数据集中的原始图像是直接裁剪吗，还是resize后再裁剪 4.LSDIR数据集较大，请问有没有在DF2K数据集上做过实验，LSDIR有包含DF2K的内容吗？ 望解答疑惑

Renzhihan

SD-Turbo results look good, but have color banding/look like painting

3

Very good results, but I am noticing color banding not present on the input images. Added "color banding" and "oil painting" to negative prompts, but it still appears. Happens even...

AIisCool

在自己的数据集上微调SD-Turbo模型

1

你好，我希望在自己的数据集上微调SD-Turbo模型，训练基于SD-turbo的SeeSR也是使用 ‘[train_seesr.py](https://github.com/cswry/SeeSR/blob/main/train_seesr.py)’这个文件吗？

yumemiso

OSError: Error no file named diffusion_pytorch_model.bin found in directory preset/models/seesr

1

请问下，给的seesr预训练模型中，并没有diffusion_pytorch_model.bin这个文件，为什么运行代码后，要求有这个文件？

EchoXu98

为什么一直出现baseball glove呢

2

作者您好，可以理解会出现错误的语义提取，但为什么经常性出现这几个词呢

donutn

About the GPU memory usage

4

Hi, wonderful work! I wonder what's the peak memory usage when training the model with HR size of 512 and batchsize of 1 for one GPU. It seams that a...

prokaryote-hgy