Minimax H3:
v3 dataset, usually used 1.00 strength. Use it for T2VA or start with an image made from an image model version of DIMStyle!
Anima:
v3 dataset. A bit cleaner and removes watermark issues. I recommend going with 0.50 to 0.75 strength. Going all the way to 1.00 can make things look much more dramatic, but increases distortion probabilities.
v1.1
Expanded the dataset to include more images and themes and whatnot. Less restrictive than before
Original Description:
Dramatic stylized art style most appropriate for fantasy/sci fi generations.
Included a couple comparison images in the examples to show differing values of guidance and weight.
Heavy Raymond Swanland influence.
Description
FAQ
Comments (3)
https://civitai.com/posts/14064222
Let me share my result of trying your LORA and follow for future contents!
The only issue I have with this LORA is characters' fingers, otherwise this LORA is amazing.
My main issue with Flux is characters are mostly standing without actions, including this monster LORA I used.
Your LORA puts an end to that issue completely, that's something remarkable.
Glad you like it! And thanks for the kind words! You've convinced me to make a Flux version using the 1.1 dataset 😊
cool
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.