Lets Gen

Overview

Lets Gen is a browser-based creative artificial intelligence platform designed to support character design, visual asset generation, and motion content creation. The application brings together specialized toolsets for text-to-image rendering, character prototyping, iterative image variations, and short-form video generation using third-party AI models. Creators can test prompts, incorporate visual references, and refine digital concepts within a centralized, credit-based studio.

Key Features

• OC Maker — Generates four customizable original character portraits per run from descriptive text prompts and selected art styles like anime, chibi, and semi-realistic.
• Reference image integration — Accepts uploaded reference files to guide visual attributes, lighting, and composition instead of relying solely on baseline text prompts.
• Multi-model image generation — Provides text-to-image workflows supporting multiple underlying models, such as GPT Image 2.5 and Nano Banana 2.1, with clear per-generation credit quotes.
• Image variations — Modifies compositions, colors, and textures while keeping core subject identities stable across iterative runs.
• AI video generator — Directs short motion sequences and camera pushes from text scenes or existing image keyframes using video models such as MiniMax H3 and Seedance 2.0 Mini.
• Story and voice integration — Bridges character portraits into deeper narrative workflows by enabling custom names, conversational settings, and synthetic voice creation.

Who It's For

Lets Gen is targeted at independent visual storytellers, concept artists, indie game designers, and content creators looking to visualize original characters and campaign artwork. It suits individuals and small creative teams who require rapid visual prototyping and motion tests without manual drawing or complex video editing tools.

Notable Strengths

The platform stands out for offering side-by-side multi-model experimentation, allowing creators to compare outputs from different image and video models using identical prompts. Its modular toolchain facilitates connected creative pipelines, letting users smoothly transfer a single character portrait into image variation, voice assignment, and video animation modes. Additionally, operational costs are transparently detailed prior to generation through a predictable Gems-based pricing structure.