TripleView is a LoRA trained on approximately 300 character sheet samples, with a strong focus on generating characters in three main views:
If this model was helpful to you in any way, please consider helping me continue creating more model for the price of a coffee.
Front · Side · Back
Training Focus
TripleView was trained primarily on human characters. It may also work with cartoon, anime, or stylized characters, but these styles were not the main focus of the training dataset, so results may be less consistent.
Its purpose is to help convert a character into a clean character sheet while maintaining a pleasant level of consistency across clothing, proportions, appearance, and overall character identity.
This LoRA is not perfect and may still produce variations in anatomy, accessories, facial details, clothing, or pose alignment. However, it generally preserves character consistency in a visually pleasing way, making it useful for character design, reference sheets, dataset creation, and further refinement.
TripleView was trained primarily to be used as part of a CharacterID workflow for LTX, where the generated three-view sheet can later serve as reference material to improve character identity preservation.
Trigger
Flux Klein Prompt: "Convert the character in the image to a Character Sheet showing front, side and back full body views"
Krea 2 Prompt: "Convert the character in the image to a Character Sheet showing a face close-up, front full body, side full body and back full body views"
After the trigger, you can also describe the type of clothing you want the character to wear.
For example, you can add outfit details right after the trigger to specify the character’s clothes, style, or overall look.
Recommended for
Character sheets
Three-view turnarounds
Front / side / back references
Character dataset preparation
CharacterID workflows
LTX pipelines
Description
The input needs to be a 1536x1024 image to improve the quality of the result. The result of the views, especially at the easy level in this version, is inferior to the 3-view version. I tried many things during training and nothing solved this, but the goal of this LoRa is to generate character sheets that can be used in my other LoRa for Character Sheet Face ID.
FAQ
Comments (9)
I provided one full shot and 2 portrait views( Front and side) to create a 4-view character sheet. Portrait looks fine, but the full body shot faces comes weird for front and side.
First, use the workflow I provided in the optional files. The input image needs to be 1536x1024. Second, this also happens because, as I mentioned in the version details, for some reason this training wasn't as good as the one with 3 views. My theory is that, since there's now a close-up present in the resulting image, the model focuses more on the close-up and ignores the other views a bit, since the close-up is very similar to the input image.
ok.@NRDX but your previews shows excellent details of the face for full body shots also especially the side ones
@anadarco12227 My input image is always a face; I don't know if you're providing a single face or a bunch of images. Try the simple setup first, then see if it works with other cases.
@NRDX i managed to get the face on full body too. the problem is the portrait image generated on the left is causing issue so had to first generate only 3 full body views . had to decrease the strength to 0.1 to generate exact face.
after making above changes it works perfectly