Midjourneyで生成した美女画像を
Midjourneyで生成した美女画像を 顔だけ抽出して制作に使えるように データベース化中 Grok Botにお願いしたら寝ている間に Codexに指示してまとめてくれてた とりあえず200枚作ってみたけど良い感じ 1,000枚くらいまで増やして公開目指そう
目录
全部条目。
所有已发布内容，最新优先。向下滚动持续加载，筛选会保留在 URL 中。
灵感@comfyui
Higgsfield promised to open-source their entire platform. They didn’t.
Higgsfield promised to open-source their entire platform. They didn’t. Let's help them. For the next two weeks, Comfy and our partners are putting up $25,000 i…
灵感@zzurcz
Estilos novos estão ficando muito bom !
Estilos novos estão ficando muito bom ! Os agentes vao conseguir aprender e replciar com referencias tbm Ent agora em "Elementos" voce pode criar : Personagens…
had the opportunity to do some AI creative direction for this campaign with the…
had the opportunity to do some AI creative direction for this campaign with the epic team at @iverson (shoutout @Dinetz for bringing me on!) it's crazy the lev…
Meet Higgsfield × FLUX 3 Image.
Meet Higgsfield × FLUX 3 Image. With Black Forest Labs' new image model, you can: > edit one detail without touching the rest > place objects with bounding box…
You have a job interview in five minutes and these two are your roommates
You have a job interview in five minutes and these two are your roommates What could possibly go wrong? Starting images made with Ideogram 4.5, and yes, the la…
灵感@comfyui
Comfy API is live
Comfy API is live Point it at a workflow JSON and it handles the rest: → Resolves your custom nodes, models, LoRAs, and Python deps → Pins it all, ComfyUI vers…
Introducing Arrow 2
Introducing Arrow 2 Our latest and most advanced models for generating precise, editable vector graphics. Higher quality. Faster outputs. Available now in App…
We're past the slop phase now
We're past the slop phase now GPT-6 ASTRA One shot this from a single reference. Prompt ↓
GPT6 太耀眼了， 导致 Image 2.5 虽然能力很强没多少人关注到
GPT6 太耀眼了， 导致 Image 2.5 虽然能力很强没多少人关注到 最近花时间整理了一下网上 Image2.5 相关的案例和提示词，做了个网站来呈现 每个案例都有提示词和来源，复制就能生成同款
AI 영상 캐릭터 시트 생성은 이걸로 종결
AI 영상 캐릭터 시트 생성은 이걸로 종결 XAZINGA님이 만드신 생성기를 써봤는데 엄청 간편하게 캐릭터 시트를 만들 수 있음 캐릭터와 착장 레퍼런스 이미지만 넣으면 힉스필드에서 공개한 방식처럼 전신에서는 얼굴을 제거한 캐릭터 시트를 만들어줌 이 방식은 생성 모델이 캐릭터의 얼굴 정…
Finally launching Mascot Design 🎉
Finally launching Mascot Design 🎉 can now design cute mascots for your app in minutes, just by chatting with AI you’ve got personality, your app should too.
I really love the naive, hand-drawn style of HEYTEA's branding, so I gave GPT A…
I really love the naive, hand-drawn style of HEYTEA's branding, so I gave GPT Astra 6 some visual references and went through a few iterations to generate a se…
【ComfyUI ReActorノードで実現する顔埋め込みとLoRA効率化】
【ComfyUI ReActorノードで実現する顔埋め込みとLoRA効率化】 ComfyUIの「ReActor」ノード、めちゃくちゃ便利ですよね！✨ ArcFaceなどを使って512次元のface embedding（顔の埋め込みベクトル）を抽出し、別の画像に自然な顔の置換や再レンダリングができちゃうそうです！
Sophisticated elegant lady candid shot📷
Sophisticated elegant lady candid shot📷 GPT- image 2 prompt 👇 Ultra-photorealistic vertical 3:4 candid luxury fashion portrait in a modern underground parking…
[Seedream 5.0 Pro Prompt] | ar 9:16 2K
[Seedream 5.0 Pro Prompt] | ar 9:16 2K Created on @TopviewAIhq @topviewaijp #Topview A highly realistic close-up portrait photograph of a young East Asian woma…
[Kling V3 Omni Prompt] | ar 9:16 4K
[Kling V3 Omni Prompt] | ar 9:16 4K Created on @TopviewAIhq @topviewaijp #Topview This is a close-up, low-angle portrait photograph of a young East Asian woman…
💌 AI 티가 가장 많이 나는 부분은 어디일까요?
💌 AI 티가 가장 많이 나는 부분은 어디일까요? 많은 분들이 ai로 만든 인물은 티가 난다고 합니다. 그 ‘티’는 어디서 날까요? 이유는 많지만, 가장 큰 문제는 바로 이목구비입니다. AI가 만든 인물은 너~무 완벽합니다. 우선 다 높고 뾰족한 코에, 큼지막한 눈과 말도 안 되는 얼…
prompt:
prompt: Create an extreme close-up 4:5 vertical front-facing smartphone selfie of a young adult woman, with her face occupying almost the entire frame. The cam…
문장 한 줄을 고감도 이미지 프롬프트로 만들어주는 스킬
문장 한 줄을 고감도 이미지 프롬프트로 만들어주는 스킬 19만 크리에이터이신 프롬왓님이 또 대박적인 걸 만들어 와주셨음 “비 오는 날 오래된 서점 감성”처럼 원하는 무드 한 줄만 입력하면 장소·의상·조명·색감까지 알아서 화보급 힉스필드 Soul 2.0 프롬프트로 뽑아줌 명령어 가이드까…
premium photorealistic live-action Chinese historical cinematic action portrait…
premium photorealistic live-action Chinese historical cinematic action portrait, an extraordinarily beautiful 23-year-old adult Chinese noblewoman riding a dar…
東方宮闕 · 鳳儀 | MJ出图Seedream5Pro优化提示词分享
東方宮闕 · 鳳儀 | MJ出图Seedream5Pro优化提示词分享 使用Akool AI视频聚合平台 @AkoolInc 概念分镜設計 #Midjourney MJ8.2 分镜細節優化 #Seedream Seedream5Pro 影片生成 #Seedance Seedance2.5 Film by @Kishe…
灵感@daaihq
🐶这组太适合人物、宠物和可爱小物了！从稚拙插画一路变成童话绘本，最后直接长成积木世界。
🐶这组太适合人物、宠物和可爱小物了！从稚拙插画一路变成童话绘本，最后直接长成积木世界。 原图 → 韩式稚拙扁平插画 → 童话版画绘本 → 乐高积木艺术 提示词放在评论区👇 快把你的作品丢进评论区，一起看看谁的照片变成积木后最可爱🥰 灵感来源:@xiaoxiaodong #gptimage2 #prompt
早前刚接触AI的时候，做过AI真人剧，如果你上传的主角图片总是被识别成真人面部，这里分享一个 Prompt 解决方案：
早前刚接触AI的时候，做过AI真人剧，如果你上传的主角图片总是被识别成真人面部，这里分享一个 Prompt 解决方案： masterpiece, best quality, 1 person, hyperrealistic but stylized, painted texture, not real photo,…
发现GPT-Image2的提示词库开源才两天，星标就冲到了18000，你还没收入囊中？
发现GPT-Image2的提示词库开源才两天，星标就冲到了18000，你还没收入囊中？ 工业级的提示词引擎、海量模板持续更新、拿来就能用——现在不存，过两周别人都在刷屏晒效果图了，你只能干瞪眼。 🔗
灵感@s1dashu
最近做了一个新的 Logo Skill，效果挺不错的：
最近做了一个新的 Logo Skill，效果挺不错的： 背景是：最近发现 grok bot, coze, workbuddy, 豆包, kiro 等等产品，其实都是在将产品 IP 形象直接作为产品的 Logo，Logo 辨识度极高，同时增强 IP 记忆，感觉挺不错的。 所以最近我的所有产品 logo 都有一个对应的可…
gpt image prompt:
gpt image prompt: A full-length casual mirror selfie of a slim young adult woman standing indoors in a modern dark-wood apartment, centered but slightly off-ax…
海报设计skill
海报设计skill 1⃣gc-minimal-zine-poster 2⃣photo-revival 3⃣pixel-style-poster-skill 4⃣scene-distillation-zine-v1-3