CompVis/taming-transformers
Taming Transformers for High-Resolution Image Synthesis
Jupyter NotebookMIT
Issues
- 1
generate white images during training
#250 opened by NikLi66 - 0
: Parameter indices which did not receive grad for rank 0: 338 339 340 341 342 343 344 345 346 347 348 349 350
#251 opened by ashwani-ver - 0
Confusion about the dimension of latent vectors
#249 opened by LiJiahao-Alex - 8
about loss of training stage2 transformers
#212 opened by CrossLee1 - 1
- 2
- 1
- 0
ModuleNotFoundError: No module named 'cutlit'
#247 opened by Polaris0421 - 5
Dockerfile/environment.yaml for CUDA Version 12.3?
#239 opened by kajc10 - 0
Is there a plan to upgrade this repo to Pytorch 2.0
#245 opened by humanely - 3
- 2
results of vqgan
#206 opened by Winnie202 - 0
- 2
gpu training hangs
#235 opened by shyakocat - 9
- 2
NCCL error
#227 opened by alex-pv01 - 2
How to get the url of checkpoint and config?
#196 opened by Catrin-baze - 2
Simply concatenating the source indices and condition indices even when they are from different codebooks?
#228 opened by abcqmars - 0
How to train your own Transformer
#241 opened by zxb-0 - 0
'VQModel' object has no attribute 'transformer'
#240 opened by Gannn12138 - 1
- 0
README Error -- yaml path
#238 opened by catsled - 0
- 0
Where is the model trained on my custom data?
#236 opened by zxb-0 - 2
Cannot use gpu to fine-tune on custom-data
#234 opened by YkiWu - 0
- 3
Vector Quantization loss rises in training
#219 opened by OrangeSodahub - 7
Invalid version: '0.10.1,<0.11'
#220 opened by EinfachYan - 0
How to do image inpainting with vqgan?
#229 opened by cannonli7 - 6
No module named 'torch._six'
#205 opened by Gianluca124 - 0
- 0
small question about the vq-vae paper
#221 opened by kwon852456 - 1
Openimages version.
#215 opened by chengjiaxiangbytedance - 0
[Code Error]
#218 opened by haozhi1817 - 0
- 2
Implementation question - Resize then crop - Model trained on low resolution image?
#214 opened by HieuPhan33 - 2
- 1
pytorch still raised "out of memory" but my PYTORCH_CUDA_ALLOC_CONF = "max_split_size_mb:128"
#194 opened by uranity - 0
wrong enviroment file
#210 opened by HuangChiEn - 0
VQGAN models license
#209 opened by Aspie96 - 0
How to calculate the negative log-likelihood from the first stage VQGAN model?
#208 opened by khanhvu207 - 1
How to train vqgan on coco dataset?
#204 opened by kevinchow1993 - 0
Hi! pretrained VQGAN face model!
#207 opened by scj0709 - 0
i want to see taming.models.vqgan.VQModel train log,
#203 opened by xiaoyaod - 0
installing into conda virtualenv (not working?)
#198 opened by agi-codes - 0
FileNotFoundError: [Errno 2] No such file or directory: '/path/to/coco_epoch117.ckpt'
#197 opened by justinday123 - 0
'Labelator' object has no attribute 'decode'
#195 opened by alihejrati - 0
Pretrained stage 2 VQGAN?
#193 opened by manuelknott - 1
Configs for some models
#187 opened by netw0rkf10w - 3
pytorch light issue
#189 opened by willyk26