Find what you need for your workflow.

RealCosplay&Anime&3D ALL-IN-ONE AnimaBase (v1.0)

MiniMax H3 workflow with StoryBoard and Official/Third-party IR Refiner — v1.0 — v1.2(nodepack 1.3.0+)

Fix AdaLN pre-bake and LoRA compatibility, including precision differences that caused pre-bake cache misses and slower sampling.

Decay

If you found this model useful, please give it a like!

lycoris_challenge.safetensors

Krea2-SAT-DirtyRealism

unet_inpaint.opt.onnx

Tutu/Ballet outfit - LoHa

Omni SR

This mirrors some models from "Omni Aggregation Networks for Lightweight Image Super-Resolution" by Hang Wang, Xuanhong Chen, Bingbing Ni, Yutian Liu, Jinfan Liu

CakeStyle.safetensors

Siglip2 Giant Opt Patch16 384 Heb 32768

This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Hebrew language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...

TeacherTelephone (電話先生/Denwa Sensei) DaiRanger / Power Rangers

ChromaAmateur.safetensors

So Vits Svc Models

These are models trained using the lesser known so-vits-svc-fork. It produces results that sound different from the more popular rvc. It's neither better nor worse, just different.

PerfecZion [Z-Image Turbo NSFW Base Model]

Utopia Optimized | VAE for low CFG

Desi Tabela - Where All the South Asian Ponies Live

风格 style MORBIS BY STX V4.safetensors

Star Wars imperial officer uniform (LTX2 and FLUX and SD 1.5 and Krea2)

lyra_illustrious_step_38000.safetensors

Krea2_Japanese film style

This LoRA model is trained with krea2-turbo, Japanese analog film style, professional photographer perspective, LoRA weight 1 recommended.