9 results
Clipdrop
Clipdrop is a collection of single-purpose image utilities rather than one general editor. Background removal cuts a subject out of a photo, cleanup erases objects, people or text, uncrop extends the frame, and the upscaler enlarges files while reducing noise. Relight adds a light source to an existing photo, replace background swaps the setting, and a text-to-image tool creates new pictures from prompts. Each tool works in the browser, and a desktop app adds a Photoshop plugin. Free accounts get about twenty uses per tool per day at standard resolution; Pro raises limits to 1,000 and unlocks high-resolution exports.
Playground AI
Playground AI is a design tool that combines image generation with templates for logos, t-shirts, stickers, posters and social posts. You describe an idea, and the editor lays out text and graphics around it, keeping the generated image on a separate layer you can edit without starting over. It connects to several external models, including GPT Image, Nano Banana and Seedream, and each generation draws from one shared monthly credit pool. Background removal, upscaling and SVG export are included on paid plans. The free tier allows five images every three hours and three monthly model credits.
Recraft
Recraft is an image generator aimed at designers who need assets rather than standalone pictures. Alongside raster generation it produces true vector output, including SVG icons, logos and illustrations that stay editable in design software. You can lock a brand palette, save custom styles, and reuse them across a project so separate images look related. Editing tools cover inpainting, background removal, mockups and upscaling, and a prompt-extraction feature describes an uploaded reference. The free plan is limited to personal use with public images; paid plans start at 1,000 monthly credits and add commercial rights and private generations.
FLUX
FLUX is Black Forest Labs' family of image models, reachable through an API, a browser playground or downloaded open weights. It covers text-to-image and image-to-image, with the FLUX 3 line handling prompts, reference images and outputs up to 4K. Klein versions are smaller and cheaper, and commercial licences allow fine-tuning and LoRA training on your own hardware. Developers pay per generated image rather than a subscription, with prices set by model and resolution. The playground runs in the browser, so you can test prompts before writing code; teams wanting a fixed monthly bill need to estimate volume first.
Adobe Firefly
Adobe Firefly is Adobe's generative AI app for images, vectors, video and audio, running in the browser and on mobile. Text prompts produce images you can then edit with generative fill, expand and object removal, and the same credit balance works inside Photoshop, Illustrator and Express. Firefly also hosts partner models from Google, OpenAI and Black Forest Labs, so you can compare outputs without leaving the app. Outputs from Adobe's own models carry Content Credentials and are licensed for commercial use. A free plan gives daily generations; paid tiers add credits and app access.
Leonardo AI
Leonardo AI is a browser-based image generator built around a token system. You write a prompt, pick one of more than eighty models, and adjust style, aspect ratio and guidance before generating. It also trains custom models from a small set of uploaded images, so a character or product keeps a consistent look across a series. A canvas mode lets you paint and generate at the same time, and separate tools handle background removal, upscaling and short video clips. The free tier gives 150 fast tokens a day with public creations; paid plans add private generations, more tokens and commercial ownership.
Midjourney
Midjourney is an image generation service known for distinctive, highly aesthetic results. It runs primarily through Discord and a web app: you send a prompt, receive a grid of four images, and refine with variations, upscaling and remixing. Parameters control aspect ratio, stylisation, chaos and reference images, and style references let you keep a consistent look across a series. It excels at concept art, illustration, product mockups and atmospheric imagery. There is no free tier; subscriptions are monthly and include a commercial-use licence and a set amount of fast generation time, with slower unlimited modes on higher plans. Text rendering remains a weak point.
Stability AI
Stability AI develops the Stable Diffusion family of open image models and a hosted platform around them. The web app generates images from text and images, with editing tools for inpainting, upscaling and structure control. Developers can access the same models through an API for products and pipelines, and many weights are published openly for self-hosting. The company also offers video and audio models. Paid credits cover hosted generation; the open models are free to run on your own hardware under their licences. It suits teams that want flexibility between a managed service and running models themselves, from indie developers to studios with GPU infrastructure.
Ideogram
Ideogram is an image generator with a focus on rendering legible text inside images — logos, posters, signs and typographic designs that most diffusion models struggle with. You describe the image and the exact wording, and the model places it with reasonable accuracy. It offers style controls, aspect ratios, and tools for remixing and extending images, plus a canvas editor for layout work. The free tier includes a daily generation allowance; paid plans add higher volumes, private generation and commercial-friendly options. It is particularly useful for social graphics, mockups and marketing assets where words must be readable, though complex layouts may still need touch-ups in a design tool.