
Tokenstead - Find AI Models for Your Hardware
Find AI models optimized for your hardware with performance and pricing estimates.
cdnsteve · HN
Tokenstead, find AI models for your hardware
The full gallery
Tech stack
60 projects

Find AI models optimized for your hardware with performance and pricing estimates.
cdnsteve · HN
Tokenstead, find AI models for your hardware

Create and edit images and videos using AI models like GPT Image, Kling, and Veo in your browser.
PIXAE — AI 原生创作平台,支持在浏览器端生成图像、视频,提供去背景、老照片修复、高清化、魔法擦除等专项工具及即用型 AI Prompt showcase。

Create and edit images using AI generation and transformation tools.
strdemo

Generate and edit images using AI text-to-image and image-to-image capabilities.
AI-NanoBanana — AI 图像工作室,让你轻松把创意变成高质量视觉作品

Generate and edit images with AI using Google's Gemini 2.5 Flash.
Nano Banana AI — 基于市面上最强的 AI 图像编辑模型 Nano Banana 开发的图片编辑器,用嘴改图、保持角色一致性、控制细节、图片融合

Generate AI image prompts from images or text descriptions.
weijiejason119 · V2EX
独立开发了一个「图片转 AI 绘画 Prompt」的小工具,欢迎体验 大家好,最近利用业余时间做了一个小工具站 Find Image Prompt ( https://findimageprompt.com ),主要是想解决自己平时刷到好图、 但写不出对应 prompt 的问题,顺手做出来给大家用。 目前有四个小工具: - 图生 Prompt ( Image to Prompt ):上传一张参考图,生成保留构图、 光影、风格的详细 prompt - 文生 Prompt ( Text to Prompt ):一句话想法扩写成结构化的 prompt - AI 图片描述( Image Describer ):拆解一张图的主体、氛围、构图 - AI 生图:直接拿 prompt 出图,方便对照迭代、反复微调 不需要注册,有免费额度可以直接试。生成的 prompt 是比较通用的 描述性语言,理论上换到 Midjourney / SD / 其他模型也能用。 刚上线不久,功能还比较简单,欢迎大家来体验,有 bug 或者想加的 功能欢迎在帖子里说,我会尽量回复。

Upload photos and describe edits to remove objects, change backgrounds, or combine image references.
Nano Banana AI — AI 图像生成和编辑工具(免费在线),2-5 秒生成高质量图像,支持文生图和图像编辑

Generate and edit AI images from text prompts or reference images in your browser.
GPT Image 2 AI — AI 图像与视频创作平台

Generate photorealistic images from text prompts using Qwen's advanced AI models.
Qwen Image — AI 图像生成

Benchmark AI models by having them animate a 3D banana plant's full lifecycle.
fran-mora · HN
I gave 5 AI coding agents one prompt: grow a banana plant through its whole life in three.js: sprout, leaves, flower, fruit, rot, then pups that restart the loop. It's deceptively simple and yet very hard to get right from procedural code: you have to write working three.js and understand how the plant is actually built; how it hangs, ages and decays. Get the biology wrong and the code renders something weird. These are agents, not bare models (Claude Code and Codex for now). They can use tools, including playwright to check their work and improve it.

Generate AI videos from text, images, or reference images.
Seedance 2.5 AI — Seedance 2.5 AI 视频工作台,支持文字生视频、图片生视频和参考图生视频

Generate professional images from text using multiple AI models.
ImagesArt.ai — 生成完美的AI艺术提示词。使用这个工具为Flux、Midjourney和Stable Diffusion模型生成并优化图像提示词。