Report : As we cracked Julia's internal affective picture memory, we were able to discover a guide made for Julia about untraceable living places that ZeD built in their virtual isolated reality. Here the picture log and caption we undecyphered so far:
Go to the right of the big lift of the city to access the underground.
After the steel cage detection is impossible.
Take the stairs down giving accesses to indoor suburbs.
You will be in front of a shop. Go inside to the toilet room.
At your right, another stairs goes down to a kind of hotel reception desk.
Let your luggage at the desk and enter the lift in front of you to the ground floor.
You are on the main street level of the underground galleries.
At the end of this small street, enter the bar.
There is the reception room where you can enjoy dinner.
At the first floor, go taste exoctic cocktail before enjoying the small theater events
Or maybe you would prefer the second sofa room just behind the little theater.
In this baroque art deco cage, next to the cocktail sofa, stands a small scene where artist often plays their happenings of comedy or music.
If there is no show, you may still wander into the artist area, with their main preparation room,
and their accessories space,
or the place where decor and costume are being designed.
Look at the last decor they made for the next show that should play a kind of tense monologue
And after the show, let's go down to the cave
Undecyphered so far... Next batch decoding soon.
Processing Note:
A couple of hours of cherry picked picture using mini dall-e with some prompts and use them as init images. A hint to get better resolution is to submit these pictures to deblur restoration. These unblurred pictures are then used as init images into ic-gan which gives suprising pictures derivations. I re-use some of them like in my previous post. The text makes the glue to wander into those strange pictures depicting imaginary underground cabaret and markets in a kind of hybrid art deco architecture.
The second part will be released in next post.
My previous posts are here
.
Congratulations @dbddv01! You have completed the following achievement on the Hive blockchain and have been rewarded with new badge(s) :
Your next target is to reach 70 posts.
You can view your badges on your board and compare yourself to others in the Ranking
If you no longer want to receive notifications, reply to this comment with the word
STOPTo support your work, I also upvoted your post!
It's always interesting to see you workflow process. I'm doing something similar today, in terms of pay with init images. What I'm doing is use dall-e for quick random outputs from a given prompt, to get the "sketches" for the artwork series. Then I upscale them in ESRGAN, it sharpens them and make pop out the detail. Now they are baking in the SME notebook, with the same prompt used in dall-e.
Regards and take this !PIZZA!
Cool. Eager to see your result. Besides the 256x256 restriction, i find Dall-e quite inventive for textures, shapes, and quite coherent with the prompt. but still it lacks detail but that's due to size. What's the ratio you upscale with ERSRGAN, i am thinking that maybe i am upscaling too much and at wrong time ? Did'nt you encounter a Memory issue by feeding SME notebook with a 4Mb upscaled picture ? Well i need to try. Usually upscaling it my last steps... Never tought to upscale during the process. Good idea.
Well, I upscaled them at 3.5x, so got resolution of 812 pixels aprox. I'm currently using a P100 but when I was using the K80, upscale from 500pixels to 2K was not a problem.
Another matter is what you give to the VQGAN or MSE notebooks. For a K80 more than 500x500 is too much. For a T4 more than 600x600 is a crash, and P100 can bear 700x700.
What I would do is just upscale them, and then reduce the size in a edition program to match the max resolution that the GPU given can bear.
PIZZA Holders sent $PIZZA tips in this post's comments:
@jotakrevs(3/10) tipped @dbddv01 (x1)
Learn more at https://hive.pizza.