YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

NUTATA v1.0 — Finetuned (Stable v15)

Cognitive video generation model finetuned with NaN-proof training.

Results

Loss: 0.1374
PSNR: 15.07 dB

Features

SparseCompressor (4 bottleneck points)
EARCP + LPOL + GQA + Neurogenesis
Text/Action/Scene conditioning
Auto GPU memory management

Usage

from huggingface_hub import snapshot_download
import sys

model_dir = snapshot_download("amewebstudio/nutata-v1.0-finetuned")
sys.path.insert(0, model_dir)

from modeling_nutata import NutataModel  # or modeling_nexus
model = NutataModel.from_pretrained(model_dir)
video = model.generate(n_frames=16, temperature=0.5)

Downloads last month: 14

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support