Dezgo
Dezgo is an online AI image and short-video generator offering controlled text-to-image, image-to-image, text-to-video and image-to-video capabilities with multiple models and image-editing tools.
Dezgo is image & design software teams evaluate for creative & design. Use this page to review pricing, integration signals, and the best alternatives before you commit.
Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.
Review official source →Used in These Packs
Quick Overview
Best for: Creative & Design
What it does
Image & Design software for decision-makers comparing workflow fit and alternatives.
Best fit
Creative & Design
Pricing snapshot
Free
Next step
Compare Dezgo with similar tools before you shortlist it.
Compare this tool before you shortlist it
Review alternatives, pricing posture, and workflow fit side by side.
Dezgo is a web-based AI generation platform that provides controlled text-to-image, image-to-image, text-to-video and image-to-video capabilities. The site exposes model selection, ControlNet-style guidance, LoRA support, upscaling and editing tools, and supports multiple models including RealDream and others listed on the page. It targets users who want to generate or edit images and short video clips from text prompts or guided by example images via an online interface.
Dezgo also highlights a new video model (Happy Horse) for generating 3–15 second clips with cinematic motion, synchronized audio and multilingual lip-sync, and offers options for resolution, sampling, guidance and output formatting.
Dezgo is an online AI image and short-video generator offering controlled text-to-image, image-to-image, text-to-video and image-to-video capabilities with multiple models and image-editing tools.
Own this listing?
Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.
Claim this listing for $29Key Features
Controlled Text-to-Image
Generate images from text while matching the structure of a given control image (ControlNet style guidance).
Text-to-Image and Image-to-Image
Standard text-to-image generation and image-to-image workflows with model selection, prompts, negative prompts, guidance and sampling options.
Text-to-Video / Image-to-Video (Happy Horse)
Generate 3–15 second clips at 720p or 1080p with cinematic motion, native synchronized audio and multilingual lip-sync (Happy Horse model).
Image Tools
Tools for removing backgrounds, upscaling (Real-ESRGAN), inpainting from text and editing images from text.
Advanced Controls
Options for LoRA extensions, control scale, control pre-processing, guidance strength, sampling steps, sampler selection, seed and upscaling factor.
Model Selection
Multiple models and versions available (examples listed include RealDream, Flux variants, Nano Banana, WAN, Kling, Veo, Sora, Seedance).
Pricing
Page title indicates 'Online Free AI Image Generator' — free access is available (no paid tiers shown on the provided page).
Use Cases
Creative image generation
Create original images from text prompts for art, concept work or social content using configurable models and guidance settings.
Guided image editing
Use an init/control image plus ControlNet-style controls to preserve structure while changing appearance, or perform inpainting and edits from text.
Short video generation
Produce short 3–15 second video clips with motion and synchronized audio from text prompts or still images using the Happy Horse model.
Image enhancement
Upscale images by factor of 2 using Real-ESRGAN and remove backgrounds for cleaner assets.
Integrations
Stable Diffusion / ControlNet
Used as underlying technology for controlled text-to-image and image-to-image generation (page references Stable Diffusion / ControlNet AI).
Real-ESRGAN
Real-ESRGAN is used for upscaling images by a factor of 2 as an available option.
LoRA
Support for LoRA extension models to modify or extend model behavior.
API
The site navigation includes an API link indicating programmatic access is available (no docs shown on the page).
Benefits
Limitations
Frequently Asked Questions
No verified FAQs are available.
Getting Started
- 1 Open the Dezgo Controlled Text-to-Image app page (https://dezgo.com/app/controlnet).
- 2 Enter a prompt describing the desired image and optionally a negative prompt.
- 3 Choose a control model and upload an init/control image (max 512x512px), or skip control to generate from text alone.
- 4 Select model, resolution, count, LoRA extensions (optional), control scale and preprocess options.
- 5 Adjust guidance, sampling steps, sampler and seed as needed, set upscaling and output format, then generate the image or video.
Support
docs
FAQ / Support and Blog links appear in the site navigation (access via site navigation).
API
API link available in navigation for programmatic access (documentation not shown on the provided page).
community
Twitter and Discord mentioned in navigation for community and updates.
status
System Status link appears in navigation for uptime and incident information.
API
Compare Dezgo with similar tools
See how it stacks up against alternatives
Related Tools
View all 386 →
Aux Machina
Aux Machina is an AI-powered image creation platform that generates custom, royalty-free visuals and offers upcoming AI-assisted image-editing tools, aimed at creators, marketers, and teams who need quick, high-quality images.
Removetext
Remove Text From Image (Removetext) is a browser-based AI tool that removes text, watermarks, or logos from images by detecting text and reconstructing the underlying background. The service offers a free workflow plus an optional Pro upgrade for faster, priority processing and higher-quality results.
Headshotphoto
Headshot Photo is an AI-powered service that generates professional-quality headshots from a few selfies in about two minutes, aimed at individuals and teams for LinkedIn, resumes, corporate profiles, and branding.
ImagePipeline
ImagePipeline is a developer-first image AI API for product and fashion commerce that generates studio-quality product shots, model swaps, and virtual try-on at scale, backed by SDKs, webhooks, and production-grade controls.
Premium Alternatives
PreCheck
PreCheck is an AI-powered facial recognition and face-search platform that lets users upload a single photo to find where that face appears across the web, and also provides reverse phone and email lookups for identity, reputation management, and fraud prevention.
Ghibli Art Generator
Ghibli Art Generator is a web-based AI tool that transforms user photos into Studio Ghibli–inspired artwork using a proprietary deep-learning style generator, offering multiple film-style filters, batch processing, and downloadable high-resolution outputs.
phopet
Phopet is a pet-focused image-generation service that trains a custom AI model from user-uploaded pet photos to produce themed, studio-quality images, upscaled prints, and merchandise-ready assets. It targets pet owners who want personalized photo packs and creative stories featuring their pets.
Aiportraitgen
AI Portrait Gen is an online AI portrait generator that creates realistic, high-quality portrait photos from a few user-supplied photos. It offers customizable locations, outfits and styles, pay-as-you-go credits (no subscription), and privacy protections for uploaded images.
