desigen

desigen copied to clipboard

Request for Fine-Tuned SD Model Weight

1

Thank you for your outstanding work. I am very interested in reproduce the model performance described in your paper. However, due to limitations in my computational resources, I am unable...

Sloan-Yang

Thanks for the nice work! How to do layout synthesis? Say you have your own image to place on the template. Can that be done? You have some examples on...

gsrujana

Hi, While the train, validation, and the test split are being created, os.listdir() method in used in the dataset class. However, os.listdir() is a system dependent method, and it returns...

Sohanpatnaik106

Thank you for releasing the code and dataset! I'm confused about [this part](https://github.com/whaohan/desigen/blob/main/layout/dataset.py#L233-L234) ``` xc = l + w / 2 - img_l yc = t + h / 2...

naoto0804

Background and Layout Evaluation

5

Am I doing something wrong? I am unable to generate a harmonized layout ### Background Training export MODEL_NAME="CompVis/stable-diffusion-v1-4" export INSTANCE_DIR="./../data/background/train" export OUTPUT_DIR="./../logs/background" accelerate launch train_background.py \ --pretrained_model_name_or_path=$MODEL_NAME \ --train_text_encoder \...

aaghawaheed

Only train layout raise error?

2

assert condition, message AssertionError: Input height (512) doesn't match model (224). the img_feature = raw_encoder.forward_features(img) img.size(): torch.Size([128, 3, 512, 512])

trouble-maker007