Qwen :
All the showcase images have been generated without upscaling :
1584x1056 (portrait and landscape) with ddim / beta + Lightning lora
5 steps and CFG 1, and a lora weight of 1.
I've only generated 2 images for each prompt, and picked one, so it gives great results without cherry picking nor upscaling !
Flux :
Trained on 29 carefully handpicked images from the movie Porco Rosso.
It is obviously close to my Kiki's Delivery Service model, but with a retro vibe because it's more grainy and less vibrant.
With a weight of 0.8, I start the prompt with :
ghibli style image of
All images are x1.5 upscaled with 4x_NMKD-Siax_200k (denoising strength 0.35 - 0.5).