Encuentra lo que necesita tu flujo.

LTX 2.5 Uncensored v1.1 FP8

UPDATED 9/10/2026: The latest LTX Video-2.5 Uncensored Turbo v1.1. fp8scaled for speed. Uncensored Gemma4 12B text encoder w/ LTX projections baked-in (no extra files needed). int8 for speed and accuracy.

6a4def5728c9df77fc509d56.safetensors

2000s Analog Core

VisionlanguageTransformer

Vision-and-Language Transformer (ViLT) model fine-tuned on VQAv2. It was introduced in the paper [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision]( by Kim et al. and first released in...

Pearly Funkybun style

A Lora based on comics from Funkybun, these are furry based comics so this Lora heavily favours furry. performs better with longer prompts.

Docling Layout Heron 101 Mlx BF16

MLX-converted weights of docling-project/docling-layout-heron-101, the larger (ResNet-101-vd backbone) variant of the Docling layout model. Apache-2.0, same as upstream.

风格 style cwelltoon.safetensors

Vit Huge Patch14 Clip Quickgelu 378.dfn5b

apple-sample-code-license

Lenovo UltraReal

SmoothMix Ultimate (Anima/Illustrious 2)

hdrEffectVAE_v20_bf16.safetensors

Eriri Spencer "Kashiwagi Eri" Sawamura (澤村・スペンサー・英梨々) - Saekano: How to Raise a Boring Girlfriend (Saenai Heroine no Sodatekata) (冴えない彼女〈ヒロイン〉の育てかた)

Support my work by subscribing to patreon!

SlimThiick.safetensors

Vit Base Patch16 Siglip 224.v2 Webli

A SigLIP 2 ViT (image encoder only) for timm. Equivalent to image tower from

corruption bodysuit

Big lamia Lora

ultimateHentaiAnimeRXTRexAnime_rxV1.safetensors

Verifitas Vit Image Detection

This model is a fine-tuned version of google/vit-base-patch16-224 on the None dataset. It achieves the following results on the evaluation set: Loss: 0.0343 Accuracy: 0.9925

Honored One / Gojo Awakening

Throughout heaven and earth, I alone am the honored one.

Shiny Nai style for pony / illustrious/anima | Goofy AI