FineToon Texttovideo

ProviderAiCoderv2
Categorytext-to-video
Licenseapache-2.0
Downloads63
Stars0

Overview

FineToon is an open-source text-to-video model released under the Apache-2.0 license, designed for developers needing a flexible pipeline for generative video content. Unlike closed-API solutions, its permissive licensing allows for deep integration into custom workflows and commercial applications without restrictive royalties. The model specializes in translating descriptive prompts into fluid visual sequences, making it suitable for automated content creation, prototyping UI animations, or building synthetic data pipelines. For engineers, the primary value lies in its balance of output quality and deployment flexibility, offering a viable alternative to proprietary models when local hosting or specific fine-tuning is required to achieve a consistent artistic style.

Highlights

  • Permissive Apache-2.0 license for commercial deployment
  • Efficient text-to-video synthesis for automated content
  • Ideal for custom pipeline integration and fine-tuning
  • Open-source alternative to proprietary video APIs

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("AiCoderv2/FineToon-Texttovideo")
tokenizer = AutoTokenizer.from_pretrained("AiCoderv2/FineToon-Texttovideo")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download AiCoderv2/FineToon-Texttovideo

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download AiCoderv2/FineToon-Texttovideo config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('AiCoderv2/FineToon-Texttovideo')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/AiCoderv2/FineToon-Texttovideo

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/AiCoderv2/FineToon-Texttovideo

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('AiCoderv2/FineToon-Texttovideo')
tokenizer = AutoTokenizer.from_pretrained('AiCoderv2/FineToon-Texttovideo')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
library_name: transformers.js
---

Create a 8 second cinematic video ad for a job post titled “We’re Hiring – Videographer”.
Style: luxury, futuristic, minimal — color palette white, gold, and black.
Scene composition:

Dynamic intro with glowing gold geometric shapes and digital film strips.

Floating icons representing creativity and media: video camera, film reel, clapperboard, 💬 DM icon.

Soft glowing text transitions.

No humans, no faces.

Subtle background motion: abstract light rays, gold particles, or smooth camera panning over modern design elements.
Text sequence suggestion:
1️⃣ “🚀 We’re Hiring – Videographer!”
2️⃣ “Create. Edit. Inspire in the world of healthcare.”
3️⃣ “CV 📩 Contact us via DM!”
Typography: bold, modern sans-serif, animated with smooth fade and motion blur.
Soundtrack: ambient cinematic music with subtle beats (no lyrics).
Final mood: professional, elegant, and inspiring — perfect for Instagram Reels, LinkedIn post, or website hero section.

View official source
Join our Telegram