A web porting for NVlabs' StyleGAN2, to facilitate exploring all kinds characteristic of StyleGAN networks

Hello,

First of all, I'd like to thank you for this amazing repository! My friend and I are examining it in this fork: https://github.com/aiksir/stylegan-web

When I run this command to build the frontend: npm run-script build, I get the following error:

(forked-stylegan-web) baris@bariss-MacBook-Pro forked-stylegan-web % npm run-script build

> [email protected] build /Users/baris/Documents/PycharmProjects/forked-stylegan-web
> rollup -c rollup.config.js


./app/index.js → dist/index.bundle.js...
created dist/index.bundle.js in 880ms

./app/projector.js → dist/projector.bundle.js...
[!] Error: 'import' and 'export' may only appear at the top level
node_modules/face-api.js/build/es6/env/isNodejs.js (1:0)
1: export function isNodejs() {
   ^
2:     return typeof global === 'object'
3:         && typeof require === 'function'
Error: 'import' and 'export' may only appear at the top level
    at error (/Users/baris/Documents/PycharmProjects/forked-stylegan-web/node_modules/rollup/dist/shared/node-entry.js:5400:30)
    at Module.error (/Users/baris/Documents/PycharmProjects/forked-stylegan-web/node_modules/rollup/dist/shared/node-entry.js:9824:16)
    at tryParse (/Users/baris/Documents/PycharmProjects/forked-stylegan-web/node_modules/rollup/dist/shared/node-entry.js:9717:23)
    at Module.setSource (/Users/baris/Documents/PycharmProjects/forked-stylegan-web/node_modules/rollup/dist/shared/node-entry.js:10080:33)
    at /Users/baris/Documents/PycharmProjects/forked-stylegan-web/node_modules/rollup/dist/shared/node-entry.js:12366:20
    at async Promise.all (index 4)
    at async Promise.all (index 6)
    at async Promise.all (index 2)
    at async Promise.all (index 0)
    at async Promise.all (index 1)
    at async Promise.all (index 0)
    at async Promise.all (index 0)
    at async Promise.all (index 0)

npm ERR! code ELIFECYCLE
npm ERR! errno 1
npm ERR! [email protected] build: `rollup -c rollup.config.js`
npm ERR! Exit status 1
npm ERR! 
npm ERR! Failed at the [email protected] build script.
npm ERR! This is probably not a problem with npm. There is likely additional logging output above.

npm ERR! A complete log of this run can be found in:
npm ERR!     /Users/baris/.npm/_logs/2020-10-15T10_02_32_356Z-debug.log

I have made a quick search on the internet but I couldn't figure it out because I'm not much familiar with Vue. Are you aware of this issue?

nvcc fatal : Could not set up the environment for Microsoft Visual Studio using 'C:/Program Files (x86)/Microsoft Visual Studio/2017/Community/VC/Tools/MSVC/14.16.27023/bin/Hostx64/x64/../../../../../../../VC/Auxiliary/Build/vcvars64.bat'

Some one creates a keanu reaves latent representation - we hook into this list

{ "latentRepresentations": [ { "title": "Keanu", "file": "Keanu.npy", "thumb": "https://github.com/name/Keanu.png", "url": "https://github.com/name/Keanu.npy" },

}

https://github.com/battleaxedotco/brutalism

We maybe able to drop this into the main view - and achieve some organization.

eg. might make sense to collapse the maths stuff into one of the tabs at bottom.

Another one for the 512 vectors. Another one for the latent directions Another one for ....

https://github.com/jasonlbx13/FaceHack/blob/b4beda81354806a13efe3c992d819fc6a9f83d65/face_gan/main.py

Given an existing star / celebrity load / save

this code could be put into a pipeline / for subparsers maybe it may have to look like photoshop layers (will raise another ticket)

def augmentation(args):

    os.makedirs(args.dst_dir+'/augmentation', exist_ok=True)

    print('Loading networks from "{}"...'.format(args.network_pkl))
    tflib.init_tf()
    with open(args.network_pkl, "rb") as f:
        generator_network, discriminator_network, Gs_network = pickle.load(f)

    Gs_syn_kwargs = dnnlib.EasyDict()
    Gs_syn_kwargs.output_transform = dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True)
    Gs_syn_kwargs.randomize_noise = False
    Gs_syn_kwargs.minibatch_size = 1
    pic = np.load(args.src_dir)
    for i in tqdm(range(int(args.num))):

        scale1 = random.uniform(-float(args.smile_range), float(args.smile_range))
        scale2 = random.uniform(-float(args.age_range), float(args.age_range))
        scale3 = random.uniform(-float(args.angleh_range), float(args.angleh_range))
        scale4 = random.uniform(-float(args.anglep_range), float(args.anglep_range))
        scale5 = random.uniform(-float(args.angry_range), float(args.angry_range))
        scale6 = random.uniform(-float(args.sad_range), float(args.sad_range))
        scale7 = random.uniform(-float(args.eye_range), float(args.eye_range))

        latent_vector = pic[np.newaxis, :]
        new_latent_vector = latent_vector.copy()
        new_latent_vector[0][:8] = (latent_vector[0] + scale1 * smile_drt + scale2 * age_drt
                                    + scale3 * angleh_drt + scale4 * anglep_drt
                                    + scale5 * angry_drt + scale6 * sad_drt
                                    + scale7 * eye_drt)[:8]
        img = Gs_network.components.synthesis.run(new_latent_vector, **Gs_syn_kwargs)
        img = PIL.Image.fromarray(img[0])
        img.save('{}/augmentation/{}.png'.format(args.dst_dir, str(i).zfill(4)))

So I've been trying out different stylegan repos - and I'm imaging a fusion of two. Basically the guts of this repo https://github.com/GreenLimeSia/GenEdi/issues/3

While it is in pytorch - I think it would be great to surface these in side bar as in the 512 vectors currently in another tab.

Also checkout artbreeder https://www.artbreeder.com/ it has some simple controls to switch up / infuse latent vectors.

Side note - the nvidia labs are switching over to pytorch - https://github.com/NVlabs/stylegan2-ada/issues/32#issuecomment-748225014

It would be very useful to have the ability to export the intermediate "Merge" images into a gif.

Also as a major feature suggestion:

• having the ability of learning and exploring meaningful latent directions