July 11th, 2025
Upload any image and re-generate the same image WITH your trained AI Character.
๐ Upload your target image
๐ Select one of your trained AI Character
๐ Click on recreate the image
Never prompt ever again!
๐ โ Launch image-to-image
June 25th, 2025
Upload any image ๐ obtain a hyper-realistic detailed prompt. ๐
Let's say you like an image on IG or pinterest
โ You upload it in the prompt generator
โ You obtain the EXACT prompt to generate that same image
โ Saves you a LOT of time (you donโt have to build your own prompts anymore)
โ Generate better images ultra realistic
Full tool tutorial / Access image-to-prompt
June 24th, 2025
It's so much better than KLING 1.6 ๐ญ
It's the SAME price as KLING 1.6 ๐ธ
We found a way to bring super cheap KLING 2.1 generations on Pykaso
Enjoy now the best image to video on the internet!
๐ Launch KLING 2.1 ๐
June 3rd, 2025
Photoshop is DEAD. Long life to FLUX.1 Kontext.
Flux Kontext is an absolute revolution in image editing and compositing.
You donโt need ANYTHING else than a prompt to edit your images.
We created a full blog article on how to use Flux.1 Kontext, read it here. ๐
Read about How to use Flux.1 Kontext? here
May 22nd, 2025
โ Improved results (consistency + AI video quality) ๐
โ Improved speed (2x faster) โก
โ Much cheaper (2x cheaper) ๐ฐ
Before all the trainings could only go up to 2000 steps
Now you can train up to 4000 steps ๐ฅ
โ More consistency
โ Less deformed body parts
โ Higher realism
Create a new AI Character to try the new Training Method 3.0
March 31st, 2025
You can launch AI influencer trainings with up to 50 images instead of 20 images previously.
If you have a good dataset for your training with quality images, you should not need to add more than 15-20 images. We increased this limit upon the request of certain users.
March 11th, 2025
January 27th, 2025
Improved
Before you could only face swap 30 pictures and 3 videos at the same time.
Now you can face swap 100 pictures and unlimited videos simultaneously.