Image Generation & Editing 10045

Scientific Figure Generator helps researchers create journal-ready figures, graphical abstracts, and schematic diagrams from plain-language descriptions. Freemium.

BananaImg is a Nano Banana AI image workspace for creating and refining images from prompts and reference photos. Free tier + paid plans.

Image2.5 是基于 GPT Image 2.5 的 AI 图像生成与照片编辑工具。输入提示词即可生成图片，或上传照片用一句话完成编辑。支持快速/思考模式、多图融合、圈选编辑，最高 4K 输出，图中文字清晰可读，可制作海报、Logo、缩略图、信息图等。免费增值模式，付费方案 Lite $9.9、Pro $19.9、Ultra $49.9。

MapMC is a Minecraft world-planning and creator-tools platform. Alongside its browser-based Java Seed Map, it offers an AI Texture Generator that turns a text idea into four 16×16 or 32×32 Minecraft-style texture candidates for browser preview, pixel editing, and PNG download. Outputs require user review and are not guaranteed original or trademark-free.

BeardStyles is a web tool for exploring beard styles before you grow or trim. Upload a photo and generate an AI preview, or browse 23 beard and mustache styles with coverage and maintenance notes. The Beard Style Finder compares options using your face shape, growth pattern and preferred length, without requiring a photo or login. You can save candidates in your browser and prepare a printable barber brief. AI previews require an account. New accounts receive three free generations once, with watermarked downloads. One-time generation packs and a monthly Pro plan are available. Previews are visual references; individual results vary.

MOSS Image is an AI image generator that transforms text prompts into high-quality images, posters, and illustrations, featuring bilingual text rendering and precise layout control.

NudeAI.com.br is the official Portuguese-language version of the 18+ AI creative platform AINude. Tailored specifically for Portuguese-speaking creators, digital artists, and adult content managers, this localized site offers a seamless, barrier-free AI creation experience with native Portuguese prompt support and flexible credit-based pricing.

DeepFake is an all-in-one AI platform for creators, offering tools for deepfake video, faceexchange, image-to-video, and music generation. Integrating top models like Kling 3.0, itfeatures 60+ viral effects to easily turn photos or text into high-quality content within asecure workflow. Make AI deepfake videos, DeepFake AI image-to-video clips, stylized images, and AI music in one workflow. Turn a person photo, prompt, or reference frame into creator-ready content faster.

Shotyard brings leading and newly released AI image and video models into one simple, affordable workspace for text, image and reference-based generation. Independent platform; not affiliated with AI model providers.

Online tool for creating and downloading personalized signature graphics SignatureGen is an online toolkit for creating personalized signature graphics. Users can generate font-based or AI-designed signatures, draw their own handwriting on-screen, and explore live signature playback and creative designs. Signatures can be downloaded in formats such as PNG and SVG, with transparent-background downloads available through the background removal tool. The signatures are intended for documents, email footers, resumes, social profiles, and personal branding.

AI studio for anime images, photo transformations, comics, and short videos Maxsa AI is an AI studio for creating anime, manga, and cartoon content. Users can generate images, transform photos into different art styles, create characters and comic pages, plan storyboards, and make short videos from text, images, or stories. The studio offers multiple AI models, visual styles, aspect ratios, and optional Agent-assisted creation.

Facecam swaps your face for a fictional character, live, on Google Meet, Zoom, Teams or Discord in Chrome. It also has voice changers and VTuber tools in your browser. Facecam swaps your face for a fictional character, live, on your video calls and streams. Pick a character and it replaces your face in real time in Google Meet, Zoom, Microsoft Teams or Discord in Chrome. The swap runs on Facecam's GPUs, so an ordinary laptop or Chromebook keeps up. Every character is made up; Facecam doesn't offer celebrities or real people. Also included: live voice changers (robot, demon, announcer, radio) and real-time AI voices; VTuber and PNGTuber makers that follow your face and talk when you talk, for calls or OBS; photo, GIF and video face swap with downloads; and free tools with no sign-up, like a mic test, webcam test, face tracking test, OBS virtual camera checker and soundboard. Who it's for: streamers and VTubers who want a persona, people who want privacy on video calls, and anyone who wants to have fun on a call with friends. Works in Chrome on Windows, Mac, ChromeOS and Linux, in browser tabs (not desktop apps or phones). Use only fictional characters, your own face, or a face you have permission to use.

Creates professional AI headshots from selfies Headshot Generator AI creates studio-style headshots from selfies. Users upload one to three photos, choose a style, and download high-resolution portraits for LinkedIn, resumes, team pages, and other professional uses. The service offers a range of outfits, backgrounds, and lighting styles, with no photographer required.

Describe a video and Treza builds the AI pipeline that makes it, then runs it on demand, on a schedule, or behind an API. Treza turns a description into a working AI video pipeline. Tell it what you want in plain language, like a daily nature Short for YouTube, vertical clips cut from a podcast, or a product spot from a written brief, and Treza drafts the whole workflow: the script writer, the video and image models, voiceover, music, captions, and the publish step. Run it once, put it on a schedule, or call it from your own code. Every step is a node on a visual canvas, so nothing is a black box. Open any pipeline to swap a model, rewrite a prompt, or add a step, then rerun just that part. Treza includes leading video models such as Veo 3.1, Seedance 2.5, Kling, and Wan, Gemini image models, and open text models like Llama, DeepSeek, and Qwen. Nodes also cover motion transfer, lip sync, upscaling to 4K, background removal, transcription, and text to speech. A built-in timeline editor handles the final cut, with layered tracks, transitions, and an AI assistant that makes edits on request. What you can do with Treza: - Turn a one-line idea into a captioned, scored Short in chat - Clip long videos and podcast episodes into vertical clips, cut cleanly between words - Run a faceless channel on autopilot with scheduled pipelines - Post finished videos straight to connected YouTube and TikTok channels - Call any pipeline as an API, including an OpenAI-compatible endpoint - Build and run videos from Claude over MCP, or with the Treza plugin in ChatGPT Pricing is simple: prepaid credits from $5, no subscription, and credits never expire. You only pay for successful runs, and every run shows what each step cost. For studios, agencies, and brands, Treza Enterprise adds deployment in your own cloud, custom nodes and workflows, and a forward deployed engineer. Built by people from film and visual effects, Treza brings the pipeline thinking of professional post-production to generative video.

Create 3D models from images for free, no sign up. Refine meshes, rig and animate characters, convert 3D file formats, and view models online. Image to 3D AI turns photos and sketches into 3D models in your browser. Upload one image and preview a model for free, with no sign up or card. Combine front, left, back, and right views into one model, or create separate models from up to 10 images at once. Choose textured or white-mesh output and an available resolution up to 1536 px. Smart Low Poly is an option during generation; AI retopology lets you set a target face count and choose quad or triangle topology afterward. Segment a model into parts, generate new textures, and auto-rig compatible humanoid or animal characters with skeletons and skin weights. Apply one of 16 motion presets across supported rig types, including idle, walk, run, jump, and creature gaits. Preview the result in 3D, then export generated models as GLB or STL, or rigged results as GLB. Convert existing FBX, OBJ, GLB, 3MF, PLY, STL, or STEP files to OBJ, STL, GLB, or PLY in your browser. Dedicated online viewers open GLB/GLTF, OBJ, FBX, STL, PLY, 3MF, and STEP/STP files; compare up to four files from the same format family with synchronized camera views. Feature and download availability vary by plan.

Browser-based studio for generating AI images, videos, and music. Everygen AI Studio is an independent browser-based workspace for generating AI images, videos, and music. Users can select from available AI models, write prompts, set generation options, and optionally provide reference media. It also offers editable templates for cinematic scenes, vertical videos, product concepts, and UGC-style content. Visitors can create without signing in, while signed-in accounts can claim eligible daily credits. Optional memberships provide additional credits, simultaneous generations, priority, and longer library storage. This studio is independent of Everygen.ai and Viewmax LLC, and its accounts and credits are separate.

Prelulu is the world’s first video roleplay companion app, bringing AI characters face to face with you. Chat, roleplay, and video call AI characters who remember your story. Prelulu is an AI companion platform for roleplay and interactive storytelling. Meet original characters with distinct personalities, voices, and backstories, or create your own by customizing their appearance, voice, and personality. Connect through text chat, voice notes, and real-time voice and video calls. Character memory helps conversations build on your shared history, making each interaction part of an ongoing story. Designed for fans of romance novels, otome games, and character-driven adventures, Prelulu lets you shape the story through your conversations, explore interactive scenes, and save favorite moments as keepsake memory cards. Free to start, with optional credits and subscriptions for premium features. All characters are fictional and AI-generated.

An AI platform for creating images, videos, ads, and social content. EaseGen is an all-in-one AI creative platform for generating images and videos in one workspace. It offers a selection of creative models, image and video generation tools, reference-based workflows, and ready-to-edit prompts for creating product visuals, ads, stories, cinematic scenes, and social content.

Online AI tool for removing text and overlays from videos RemoveText.video is a browser-based AI tool for removing hardcoded text, captions, subtitles, logos, and authorized watermarks from videos. Users can preview and configure a video locally before uploading it for processing. The tool supports manual area selection and automatic detection for fixed text, and aims to reconstruct the background without cropping the video.

AI tool for removing unwanted objects from videos Video Object Remover is an online AI tool for removing unwanted people, objects, logos, watermarks, and timestamps from video. Users select a frame, describe the object, confirm the AI-generated mask, and let the tool rebuild the background frame by frame. Original audio is kept. Tool 1 supports manual selection and free processing of short clips; paid credits unlock longer clips and watermark-free output. Tool 2 can regenerate a scene from a text description without requiring object selection and is paid only.

removebackground.me is an AI background remover and browser-based photo editor. Create a transparent cutout, preview it for free, and refine it for product photos, portraits, and social content. removebackground.me removes image backgrounds automatically and opens the result in a browser editor. Upload a JPEG, PNG, or WebP image, paste one from your clipboard, or provide a public image URL. After processing, keep a transparent PNG or replace the background with a color, gradient, photo, or your own image. Refine edges with erase and restore brushes, then crop, reposition, adjust colors, apply filters, and add an outline or shadow. Low-resolution previews and editing are free; one credit unlocks a full-resolution result. The site supports product images, marketplace listings, profile pictures, and social graphics.

AI workspace for generating video, images, music, and voice Seedance 3.0 is an online AI creative workspace for generating videos, images, music, and voice. It offers multiple AI models and workflows for creating and refining media from prompts and reference assets. Users can choose between memberships and pay-as-you-go credits, with the credit cost displayed before generation. Exact video costs vary by model, input type, duration, resolution, and output count.

AI generator for consistent pixel art game assets and animations SpriteCook is an AI pixel art generator for game developers. It creates characters, items, props, UI elements, animations, tilesets, backgrounds, logos, and complete asset packs from text prompts or reference images. The platform maintains consistent visual styles across assets and animations, produces true pixel art on a real grid, and exports transparent PNGs and sprite sheets ready for Unity, Godot, Phaser, GameMaker, or other engines. It also connects with AI coding agents such as Claude Code, Cursor, and VS Code Copilot.