GPT Image 2 AI — AI 图像与视频创作平台

xiaoboai · V2EX

做了一个 GPT Image 2.5 图片网站，可以在一个工作台中生成和编辑图片 大家好，分享一下我做的图片生成和编辑网站 GPT Image 2.5： https://gptimage25.biz/ 它是一个网页工作台：想从零做图，就输入提示词；已经有图片，就上传参考图并描述想修改的地方。并且可以一次生成多张图片，可以更快速拿到符合要求的结果。 目前接入了 Flare 和 Sunburst 两个模型，两者都支持文生图和参考图编辑。输出可以选择 1K 、2K 、4K ，也支持方图、竖图、横图等比例。比如做内容配图，可以先描述画面；做产品视觉，可以带上参考图，尝试调整背景或整体风格。 网站目前是英文界面，生成需要登录并消耗积分。注册可以赠送积分，体验生成一次。 官方模型的介绍在这里： https://openai.com/index/introducing-chatgpt-images-2-5/ 如果有官方账号，也可以直接在官网使用。 想听听实际使用中的反馈：从输入提示词到拿到图片，哪一步最影响效率？如果你经常需要修改现有图片，最希望这种工具做好

langren · V2EX

[分享创造]Doki Doki Dialog Generator Doki Doki Dialog Generator ( https://dokidokidialog.com/) lets you easily create visual-novel-style scenes using characters and backgrounds from Doki Doki Literature Club!. It provides an intuitive interface for fan fiction writers and meme creators to customize expressions, text, and layouts without any coding.

微软 TTS (Text-to-Speech) 文字转语音下载器 — 一键播放或下载 微软 TTS 文字转语音 合成的音频。支持所有官方提供的语音和声音选项。支持SSML语法。每月享免费用量。量大者可升级Pro Plan，固定便宜费用无限使用。摒弃按量收费。支持支付宝

@TopvonA · X

@bryanodong · X

I was tired of getting only white people voices with AI, so i vibe coded this. can you guys try it out ans share the results i would love to see what you come up with. its a text-voice naration web app .

@bestaipacks · X

Qa prompt tool Let's you fix bad ai prompts for free, gives you a score and saves your improved versions. Paid account gets more qa reports, access to better models and ability to re run improved prompts on just about any model

@zoxilsi · X

@JonnyD · X

I'm happy to announce "Mash" A local first browser based app for compiling notes and ideas on an infinite canvas. Make as many notes as you want, drag and drop to "Mash" them by combining. Create "sequences" that allow you to export a pdf with each sticky as it's own page. Drop in PDF or DocX or images to easily browse the file and select your favorite clippings to a new canvas, and manipulate them or export them how you want to. Drop a GIF to get all the individual frames. Mash features a roster of cute food themed mascots because this is your infinite textual stove top. Pull in some ingredients, mash them together, stitch them together, arrange them into a flow chart, whatever you find useful, and then get out quickly. Mash is for the little moments that speed up work, and the spontaneous thoughts that inspire new directions. There is no fancy AI feature, no data collection, no login, just a utility for you. Free open source licence. Run it offline if you want

@Ex3NDR · X

Few days ago Happy had a birthday. Tried to refresh one of the most neglected part of it: our Happy Website: also i built a new harness called “rig”. i started to use at work recently instead of codex/claude code and i liked how it does work. i want to share this with everyone. it is a codex and cause code reimplemented using Pi, but keeping native prompts and expanded a little for uniformity (like added workflows to codex yay!). when something new released that is worthy of porting - i ask Sol to mim for prompts or read sources directly and i can have a feature within an hour. why this is needed? i was constantly blocked by the needing of integrating a lot of models together, which each has their own harness or many doesn’t have any, but i didn’t want to go too far from native and don’t like the idea of extensions - i want experience to be the same everywhere. i think configuration > extensions. more soon

@fortsignal1 · X

afitnerd · HN

Text adventure to learn skills and agents