Full Version: Funny thing at the opposite of Moi ;)

Show messages: 1 … 2122-2141 2142-2161 2162-2181 2182-2201 2202-2221 2222-2241 2242-2261 … 2782-2796

From: Frenchy Pilou (PILOU)

11 Aug 2023 [#2182]

Playground day 234
Gaugan Original

Playground
100 big zoom : https://imgbox.com/g/myMV5ZHNd1

From: Frenchy Pilou (PILOU)

12 Aug 2023 [#2183]

Leonardo - day 23
10 000 portraits : https://moiscript.weebly.com/leonardo-10-000-portraits.html
100 big zoom : https://imgbox.com/g/7s7NuNn1D6

From: Frenchy Pilou (PILOU)

13 Aug 2023 [#2184]

Leonardo 100 portraits day 24
10 000 Portraits https://moiscript.weebly.com/leonardo-10-000-portraits.html
100 big Zoom : https://imgbox.com/g/oE1YwSKOEa

From: freeman (FERNANDLEGGERO)

13 Aug 2023 [#2185] In reply to [#2094]

Dear Pilou, I followed your instructions to try to test and train a model with Leonardo AI. I also signed up for a month so that I would have more possibilities.
However, the result I got with my pre-raphaellite girls was very disappointing compared to yours.!
I have also the impression that many of your portraits have then received post-processing afterwards (floral insertion, front and back of the ubject etc.).

I also encountered some difficulties with your nice suggestions of 25 May on this blog: with a found image on the Net prompt "post appocalyptic devastated city".
In this case I wasted dozens of tokens, because most templates simply leave everything blank.
The only one that started working was the Dreamshaper v. 7 model , and only with: Controlnet activated and only if selected on: depth or image, otherwise it produces nothing.
And also I got different designs from yours that you obviously used a different template....

I believe that your valuable blogs, and your fantastic inventions would be more appreciated if you also indicated some of the steps you encounter: type of model, slides, promt etc. I think thet a fuller step by step would be much appreciated by all your loyal followers!

Many Tanks

Fernand Leger

From: freeman (FERNANDLEGGERO)

13 Aug 2023 [#2186] In reply to [#2185]

Another small question. How do you get portraits in which several studies appear? Even 10 faces in different angles.

Does something have to be written in the prompt?

From: Frenchy Pilou (PILOU)

13 Aug 2023 [#2187] In reply to [#2185]

I made a little tutorial 3 days ago! :)

here the 3 result with several intensities...

0.17

0.19

0.3

Absolutely no post process! Leonardo makes all!
it's that i made every day with any image! I have no time for make post process!
https://moiscript.weebly.com/leonardo-10-000-portraits.html

From: Frenchy Pilou (PILOU)

13 Aug 2023 [#2188] In reply to [#2186]

<<
Another small question. How do you get portraits in which several studies appear? Even 10 faces in different angles.

Does something have to be written in the prompt?

The different angle are given by the different original images taken!

I never write a prompt except the 3 ones ...
"Portrait"
"Color Portait"
or last day
"Color Portrait smiling"
for the number day 24 as you can see it 3 posts above!
one of the result! :) (i will try to refind the original)

Give me an image and see the result i obtain... with my Preraph data set!
no more than these 5 images!!! My "Preraph" data set!!!

I believe that was this one! :)
here 0.17 so maybe with a more intensity 0.19

You have never the same result if you don't use the seed number!

As you can see here some post process must be made... :)
I don't make it i just will generate an another image! :)

From: Frenchy Pilou (PILOU)

13 Aug 2023 [#2189]

With this one it's not my "Preraph" as describe following on the image tutorial! ;)
Look at the prompt it's only "post appocalyptic city"
No post process ! The "Finetuned" is on the list of them given by Leonardo

From: freeman (FERNANDLEGGERO)

13 Aug 2023 [#2190] In reply to [#2189]

Tanks Pilou now try again :-)

From: freeman (FERNANDLEGGERO)

13 Aug 2023 [#2191] In reply to [#2190]

Tout va bien, super Pilou ! toutes les expériences se sont bien passées !

Je pense que j'ai compris que le truc c'est quelques photos dans le modèle, 5 suffiront. J'en avais mis 19 et elles étaient confuses.
Bien sûr, je me trompe souvent de main, mais il suffit d'en prendre plusieurs et de ne garder que les bonnes.

La seule chose qui ne fonctionne toujours pas est la post appocalyptic city, qui avec le modèle isométrique ne fonctionne pas pour moi, il fonctionne avec d'autres modèles cependant.

Merci encore Pilou !

From: Frenchy Pilou (PILOU)

13 Aug 2023 [#2192] In reply to [#2190]

FAQ advises 8 to 15 images for training models!

The flowers added are just the flowers added automatically from the original image!

About my prompt "portrait" you are not obliged to input a so short one!
But as the result is sufficient for me...you can add any prompt!
(no more 75 words) will be not take in count in Leonardo!!!

II have this very rustic negative prompt! But you can add anything you want!
"nfsw signature blurry"

From: Frenchy Pilou (PILOU)

13 Aug 2023 [#2193]

for the fun with the same "classic" original image above...
"color portrait similing post appocalyptic city"
with different intensities...it's endless and without efforts! :)