Image, Video & Audio Generation

32 free image, video & audio generation tools in the AI Tools collection — every one runs in your browser with no signup and no uploads.

AI Voice Provider Comparison Table

Compare ElevenLabs, PlayHT, OpenAI TTS, Murf, and others at a glance

AI Voice & TTS Model Comparison

Compare ElevenLabs, OpenAI TTS, Google Cloud, AWS Polly

Automatic1111 WebUI Settings Guide

Understand every Automatic1111 setting tab with recommended values

ComfyUI Node Reference Card

Quick reference for core ComfyUI nodes with inputs and outputs

ComfyUI Workflow Planner

Plan ComfyUI node workflows with VRAM and speed estimates

DALL·E API Playground

Test DALL·E 3 image generation directly from the browser with your API key

DALL·E 2 Size Picker

Pick the right DALL·E 2 size (256/512/1024px) with cost comparison

DALL·E 3 Revision Mode Guide

Use DALL·E 3's natural-language editing with precise instruction patterns

DALL·E 3 Size & Quality Picker

Choose DALL·E 3 size + quality combo and see cost per image

ElevenLabs Voice Settings Advisor

Find ideal stability, similarity, and style settings for ElevenLabs voices

Passive Voice Detector & Rewriter (BYO-key)

Find and optionally rewrite passive voice in LLM-generated text.

Midjourney Aspect Ratio Calculator

Convert pixel dimensions to Midjourney --ar flags instantly.

Midjourney /blend Mode Guide

Plan image blends with optimal image count, weight, and dimension advice.

Midjourney Chaos Parameter Guide

Understand --chaos 0–100 with use-case suggestions and copy-ready flags.

Midjourney Character Reference (--cref) Guide

Use --cref and --sref for consistent characters and styles in Midjourney

Midjourney /describe Reverse Engineer Guide

Use /describe output to extract reusable style tokens from reference images.

Midjourney Pan & Zoom Mode Guide

Use Midjourney's pan and zoom-out features for cinematic expansions

Midjourney --quality (--q) Parameter Guide

Choose the right --quality value for your Midjourney image and save credits

Midjourney --style raw Guide

Use Midjourney --style raw for minimal MJ aesthetic with maximum prompt control

Midjourney Seed Manager

Save, label, and reuse Midjourney seed numbers for consistent results.

Midjourney Stylize Explorer

Preview how --stylize values (0–1000) affect your prompt output.

Midjourney Tile Mode Guide

Generate seamless pattern prompts optimized for the --tile flag.

Midjourney Version Comparator

Side-by-side capability matrix for Midjourney v4 through v7.

OpenAI TTS Voice Picker

Compare OpenAI TTS voices (alloy, echo, fable, nova, onyx, shimmer) by use case

SDXL Extension & Fine-tune Model Guide

Navigate the SDXL model ecosystem: base, refiner, fine-tunes, and adapters

SDXL Native Resolution Picker

Choose SDXL-optimized resolutions to avoid quality degradation

SDXL Turbo & Lightning Guide

Configure SDXL Turbo and Lightning models for 1–4 step generation

SDXL Base + Refiner Workflow Guide

Configure SDXL base and refiner split for optimal quality

TTS SSML Markup Builder

Build SSML tags for pauses, emphasis, and prosody in AI voice generation

Voice Clone Recording Quality Checklist

Check your recording setup meets quality requirements for AI voice cloning

Voice Clone Training Script Formatter

Format voice clone training scripts with phonetic diversity requirements

SSML Prosody Builder

Build <prosody> SSML tags for pitch, rate, and volume control in TTS