The pack is now the whole studio: one Workspace panel with the models, prompts, camera, LoRAs, references, canvas, painting and grading, sampling the render itself, and a Detailer that lists its passes.

Krea 2

Status

Listed

ModelCivitai

Live Wallpaper Fast Fusion

🧬 Live Wallpaper Fast Fusion – 8 to 10 Step Edition

CheckpointWan Video 14B i2v 720p

Status

Listed

ModelHugging Face

Index Tts2 Metal

bilibili.model.use.license.agreement

OtherIndexTeam/IndexTTS-2

Status

Listed

ModelExternal source

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 ⚠️🚨

Text modelgoogle/gemma-4-E4B-it

Status

Listed

ModelHugging Face

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...

Videomae Base Finetuned Kinetics Allkisa Crop Background 0307 Clip Duration Abnormal38

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.1985 Accuracy: 0.9329

OtherMCG-NJU/videomae-base-finetuned-kinetics

Status

Listed

ModelExternal source