Tensor.Art
Create

DiT AniTrait [2xIMG-MT-HunyuanDiT]

LORA
Original
theway2377

Updated:

v1_20DiTE5
v1_25DiTE7
v1_25DiTE8
vA0_20HQE7
vA0_20HQE9
347

In Collaboration with theway2377: https://tensor.art/u/605424332419789926

Generate simple anime style portraits for Hunyuan DiT.

(Currently Works for Simple Background Only!)

For prompting please see image generation data or each version's description.

Version Explanation:

-v1 is the release version. v1_20 uses a bit different parameter than v1_25.

-vA0 is early test version. A bit unpolished but I think it kinda works so you can try that also.

Feel free to try it! And roast me on Discord if this is crap!

Thank you for using this LoRa on your image generations.

Version Detail

Trained by Tensor
HunYuanDiT
5
Prompting goes like this: portrait, a girl / a boy and then describe your desired character. You can also use your booru tag prompt and use the enhance button. Then put trigger words at front (or at the back, up to you but I personally recommend putting it at front). Known issue: -Currently works best for simple backgrounds with chillax prompting. -Complex generation requires using person yolov8 ADetailer model for clearer character generation (or if you think that the character is fine, just use face yolov8 model).

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated images

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.