V3.0 working only comfy ui whit this custom nodes https://civarchive.com/models/2087992?modelVersionId=2434475
Based Nikon photos
Flux Fix LoRa: https://civarchive.com/models/1521421/flux-fix-for-reality-master-v20
Basemodel use for realistic training,
Description
FAQ
Comments (10)
At first I thought it was a FLUX model
right???!!!
Idk what is animax engine but i love it 😍
Shit flux is better.......
works also great as img2img from illu! thx :) edit: you did such an amazing job carrying over the anatomy style from Illustrious, something that mno other "real" illu checkppoint I have tried has been able to preserve. What is your secret sauce? :)
The AniMax Engine is an integrated modelling system that combines several elements of diffusion-based generation (refiner, ControlNet, hires fix, adetail).The double clips (text encoders) have been retrained specifically for the model.The double text encoder layers have a cross-attention scale value of 0.6-0. 7 optimized so that text instructions do not clash with visual patterns
Double timing
The key to style preservation is when to activate the refiners:
First 50% generation: only the rough anatomical skeleton (e.g. pelvic-shoulder line)
Last 50%: ControlNet (OpenPose) and the refiner work in parallel, so details (e.g. muscle tone) do not overwrite the basic structure.
The secret is not in a magic promt, but in making body composition the primary constraint at every stage of generation. Other models often "forget" this once they start adding textures or shadows.
thank you for the explainer! I also just realized you are the creator of AniMax as well which I will check out now.
I generally dislike the realism/IQ of Illustrious, but this one is really good and one of the few that handles Pony LoRAs really well (both character and concept). Nice job!
any recommendations for sampler, steps etc
7 months and not 1 reply.. what a great community .. NOT !!


