Tensor.Art
Create

Koji

CHECKPOINT
Reprint


Updated:

10

Please use original: https://tensor.art/models/601239307694408546

creator: Ikena

Kojis goal are easy to archive high quality anime images. Model is trained on hassaku.

My Discord, for everything related to anime models.

Sponsors:

Mage.space with its amazing creators program supports all kinds of creators like me! Preinstalled with 80+ high quality models, hundreds of loras and a new animation feature, join their discord community here!

SinkIn.ai hosts the best Stable Diffusion models on fast GPUs. You can run Hassaku at: https://sinkin.ai/m/76EmEaz

Supporters:

Thanks to my supporters RiyuSETI, Jelly, Kodokuna and Gpr0mpt on my patreon!

You can support me on my patreon, where you can get other models of me and early access to model versions.

_____________________________________________________

Using the model:

Use mostly danbooru tags. No extra vae needed. For better promting on it, use this LINK or LINK. But instead of {}, use (), stable-diffusion-webui use (). Use "masterpiece" and "best quality" in positive, "worst quality" and "low quality" in negative.

My negative ones are: (low quality, worst quality:1.4) with extra monochrome, signature, text or logo when needed.

Use clip skip 2 with sampler DPM++ 2M Karras or DDIM.

Don't use face restore and underscores _, type red eyes and not red_eyes.

_____________________________________________________

Loras:

Every LoRA that is build to function on anyV3 or orangeMixes, works on koji too. Some can be found herehere or on civit by lottalewdsTrauter, Your_computerekune or lykon.

_____________________________________________________

Base model for koji is hassaku.

Black result fix (vae bug in web ui): Use --no-half-vae in your command line arguments

I use a Eta noise seed delta of 31337 or 0, with a clip skip of 2 for the example images. Model quality mostly proved with sampler DDIM and DPM++ SDE Karras. I love DDIM the most (because it is the fastest for model testing).

Version Detail

SD 1.5
20
8
Sampler: DPM++ 2M Karras Koji V1 inpainting version. SD 1.5 changed with SD 1.5 inpainting. Use for img2img -> inpaint. Because i rip SD 1.5 out and put SD 1.5 inpainting in, some parts of koji gets damaged with it. Use it in combination with the base model.

Project Permissions

Model reprinted from : https://civitai.com/models/41916

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Comments

Related Posts

The image generated by the model, publishing a post will appear here
Describe the image you want to generate, then press Enter to send.