# Tips to creating a sequential GAN image generator

**URL:** <https://discuss.pytorch.org/t/tips-to-creating-a-sequential-gan-image-generator/91538>\
**Category:** hackathon\
**Created:** [August 4, 2020, 1:41am UTC](https://discuss.pytorch.org/t/tips-to-creating-a-sequential-gan-image-generator/91538 "2020-08-04T01:41:02Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![santi22](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/santi22/32/27445_2.png) [@santi22](https://discuss.pytorch.org/u/santi22)\
**Post date:** [August 4, 2020, 1:41am UTC](https://discuss.pytorch.org/t/tips-to-creating-a-sequential-gan-image-generator/91538/1 "2020-08-04T01:41:02Z")

</div>

I would like to train a GANs model that can generate 1 output image from a set of 3 images.

- Do you have any tips on this?

- Will the GPU capacity needed to train this be really high? I just requested 1 P optimized instance on AWS to use a p2.xlarge instance. Will that be enough or do I need a p3.2xlarge ?