Find what you need for your workflow.

Probe Ade20k 40k S512 C9 In21k

Linear segmentation probe on the canvas features of canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02.

Siglip2 Giant Opt Patch16 384 Hau 32768

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

model.safetensors

Techno mysticism

A lora for PCB style weird aesthetic of short circuit board, electronic, cables and religious figures.

Wet hair - Illustrious - wet_hairV1.safetensors

Eitopondo Style

Eitopondo style

Live Wallpaper Fast Fusion

🧬 Live Wallpaper Fast Fusion – 8 to 10 Step Edition

Index Tts2 Metal

bilibili.model.use.license.agreement

6798b1ec5ee2449ce7c13fc2_000001000.safetensors

6a4d10c2ecd4419afef50cd6.safetensors

ZyloO's Characters 🙂

Yurisaki Mika(swift swing)[百合咲ミカ] -maimaiDX ANIMA

Some details, such as "six wings", may be a bit inconsistent. You can increase their weight by typing something like (six wings:1.5) to improve the result.

Gemma 4 E4B It Uncensored Heretic

🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨

Taeh3

An unmodified mirror of taeh3.safetensors from madebyollin/taehv, the tiny autoencoder for the MiniMax-H3 video latent space. It decodes a whole clip of latents to video far more cheaply than the full H3 VAE, which...

Bigvgan v2 24khz 100band 256x

[[Paper]]( - [[Code]]( - [[Showcase]]( - [[Project Page]]( - [[Weights]]( - [[Demo]](

model.safetensors

model.safetensors

model.safetensors

Sam3

This repository mirrors the official Segment Anything Model 3 (SAM 3) weights released by Meta Superintelligence Labs. SAM 3 is a unified foundation model for prompt-driven segmentation in images and videos. It...