aimagelab/multimodal-garment-designer
This is the official repository for the paper "Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing". ICCV 2023
PythonNOASSERTION
Issues
- 1
- 0
- 1
How to download the UNet model?
#27 opened by wly-ai-bj - 0
- 0
can you provide your train code
#26 opened by fengyun691340 - 0
training code
#25 opened by hw-liang - 0
- 3
File "F:\AI\multimodal-garment-designer-main\pipes\sketch_posemap_inpaint_pipe.py", line 519, in __call__ mask, masked_image = prepare_mask_and_masked_image(image, mask_image) TypeError: prepare_mask_and_masked_image() missing 2 required positional arguments: 'height' and 'width'
#17 opened by StartHua - 0
- 0
- 1
- 1
Loading vae error
#20 opened by zengjie617789 - 1
environment setup
#16 opened by amansaini25 - 2
how to make keypoints
#18 opened by StartHua - 2
Preprocessed Input
#11 opened by rohitpaul23 - 1
- 1
Generating complete model images using pose map, textual description and shape of garment only
#13 opened by madmaverickminion - 1
Gradio setup
#12 opened by raincrash - 1
Training from scratch?
#15 opened by yisol - 3
Run without sketch
#10 opened by rohitpaul23 - 0
scheduler_config.json
#14 opened by herry101st - 1
- 1
training code
#9 opened by haizhu12 - 10
inference result quality
#6 opened by zhangai6666 - 2
- 2
FileNotFoundError: [Errno 2] No such file or directory: '/data3/viton/viton-hd/test/im_sketch_unpaired/05006_00_11001_00.png'
#5 opened by zhangtao22 - 4
run inference with released weights
#4 opened by zhangai6666 - 1
When the code and dataset will launch?
#3 opened by harshbhatt7585 - 3
- 1
train a control net and use it with SD?
#1 opened by loveofcsdt