NOTE : Base model : Z Image Turbo & Flux1
Showcase images were created with ComfyUI and are in PNG, include metadata & workflow.
VERY IMPORTANT NOTE :Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption
Description
Model trained on civitai with 84 images.
Recommended resources : Fluxmania
Recommended settings : Recommended settings : dpmpp_2m / sgm_uniform / 25 - 30 steps / flux guidance : 3.5
Weighting : around 0.7
FAQ
Comments (5)
Is it a cinematic haze effect?
yes a little in this spirit, a diffuse subdued light
Your creativity is mind-blowing; no one can achieve images like these or other images you have here and in other checkpoints/Lora. Absolutely amazing stuff, dude. You keep inspiring me to generate images like these.
I like to give a little freedom to the models I finalize and I am often very pleasantly surprised. I steer a little in the direction I want, intervening on both the latent and the prompt, but without freezing the rendering too much. The Fluxmania checkpoint series has allowed me to have a good tool, both versatile and full of artistic creativity (Kreaminia integrates 17 of my loras). Thank you for your words, it is very touching and it is a pleasure to be a source of inspiration
@Adel_AI Wow, thanks for sharing a bit of your technique! The balance between steering and allowing for surprise makes perfect sense, and it's clearly working brilliantly. I'll have to check out the Fluxmania series more. Seriously inspiring stuff. Thanks again!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.