k-l-lambda / stylegan-web Goto Github PK

This is an amazing work you are doing here!
I've forked your code and thought of adding Docker and Docker-compose for making it way more easy to start.
See https://github.com/valentinvieriu/stylegan-web

Are you interested in having this approach in you repo?

So I've been trying out different stylegan repos - and I'm imaging a fusion of two.
Basically the guts of this repo
GreenLimeSia/GenEdi#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 -
NVlabs/stylegan2-ada#32 (comment)

I installed this app under windows, setup everything, but I get this noise for any model. What's happened?

I have RTX 3060, is this compatible?

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?

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 ....

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'

@app.route('/generate', methods=['GET'])

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)))

Hi,

When I run the project locally, clipboard functionality works fine. However, when I try to run the project on a server (for example, AWS EC2 instance), copy to latent code buttons and hash copy-paste in merger page do not work because of this issue: navigator.clipboard is undefined

What I've learned is clipboard doesn't work with unsecured applications. So, it's necessary to run flask over HTTPS if you would like to use clipboard functionalities. If you think that this functionality is not necessary, at least it might be good to add a note in README.md.

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

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"
},

}