FlatFrame Wan-14b T2V

LORA
Original


Updated:

FlatFrame – Stylized Flat Illustration Text-to-Video LoRA for Wan 2.1 14b t2v

FlatFrame is a finely tuned LoRA for Wan 2.1 (14B,t2v), designed to generate visually compelling text-to-video outputs in a flat-colour, vector-style illustration aesthetic. This model is ideal for creators, animators, and designers seeking a stylised, minimalist look inspired by modern digital illustration and motion design.

🔍 Overview

Trained on a compact yet diverse dataset of 30 curated images and 5 short videos, FlatFrame leverages 3,000 steps of Lora fine-tuning to achieve a consistent and clean animation style. The model renders smooth visual narratives with simplified color palettes, sharp edges, and a distinct 2D look—perfect for explainer videos, animated content, or aesthetic generative art.

🛠️ Training Details

  • Base Model: Wan 2.1 – 14B T2V

  • Steps: 3,000

  • Dataset: 30 static illustrations + 5 stylized animation clips

  • Visual Style: Flat colors, high contrast, minimal shading, illustration-inspired

🌟 Ideal Use Cases

  • Flat-style animated video generation

  • Explainer and motion graphic assets

  • Educational and storytelling visuals

  • Generative art with minimalistic design language

🧠 Prompting Tips

To achieve optimal results, include terms like:

  • "flat illustration style",

  • "vector aesthetic",

  • "minimalist color scheme",

  • "2D animation scene" in your prompts.

Version Detail

WAN_2_1 Text2Video
3000

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts