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
FAQ
Comments (18)
holy shit this might be perfect for sheets, can it work on non humans? i might try it anyways
andd maybe a krea2 version?
So the last time I tried training an "Edit" model for Krea 2, I felt it was too much of a workaround and didn't perform very well, so I didn't try again. But I might try again soon.
This is very helpful, thank you!
The 4views is even more helpful. It came right when I finished my workflow of 4 view using your 3 viewes Lora/WF. I'm going to use yours 4view now :-)
@vladulidlo Yes, but the quality of the views dropped a bit compared to the 3 views, and my theory is that because the close-up is now present, when I trained the model it gave more importance to the close-up than to the views, and this sometimes caused the quality of their faces to be poor. This didn't happen with the 3 views because there's no close-up there.
@NRDX Thank you, this is good to know!
love this, it also works with "Convert the character in the image to a Character Sheet with 4 parts, showing close up face, full front, full side, and full back body views.", side view is not perfect but i prefer it like this.
Can one use multiple reference images to produce better results or does it only work with a single image?
I haven't tested it, but it probably works; it will extract as much detail as possible to generate the sheet.
A great Loras! It just struggles a little bit with bra, but you just need to adjust the prompt.
I think the best results come from just providing your face and describing your body.
And it works good with my loras! Tank you!
Love it, it's easy, it's fast.
这是一个非常棒的lora，但是头身比有点难调整，头太大了。
This is a great lora, but the head to body ratio is a bit difficult to adjust as the head is too big,
I think that if you provide an input image where the body is present, it will adjust the aspect ratio better. The problem, from what I've noticed, is when the reference only has the head.
I am getting a bunch of these warnings: [WARNING] lora key not loaded: diffusion_model.transformer_blocks.4.attn1.to_k.lora_B.weight
[WARNING] lora key not loaded: diffusion_model.transformer_blocks.4.attn1.to_out.0.lora_A.weight
[WARNING] lora key not loaded: diffusion_model.transformer_blocks.4.attn1.to_out.0.lora_B.weight
[WARNING] lora key not loaded: diffusion_model.transformer_blocks.4.attn1.to_q.lora_A.weight
[WARNING] lora key not loaded: diffusion_model.transformer_blocks.4.attn1.to_q.lora_B.weight
[WARNING] lora key not loaded: diffusion_model.transformer_blocks.4.attn1.to_v.lora_A.weight
[WARNING] lora key not loaded: diffusion_model.transformer_blocks.4.attn1.to_v.lora_B.weight
[WARNING] lora key not loaded: diffusion_model.transformer_blocks.4.attn2.to_k.lora_A.weight
Are you using other Lora models together? If so, disable them one by one to see which one is causing this.
@NRDX I found the problem, I was using a a lora called TripleView_v1.0_FluxKlein9b.safetensors. Was that an earlier version of this lora?
@dennistaveras705 This is the Lora model.
@NRDX Strange because I downloaded this lora CharacterSheet4Views_flux_klein9b.safetensors and this one works good