Keep on to blur preview images; turn off to show them clearly
We all need an awkward '90s holiday photoshoot with our siblings. If you missed the boat (like I did), you're in luck - I wrote some prompts you can use with Nano Banana Pro ✨ Upload a photo of each person and then use the following: "An awkward vintage 1990s studio photograph using the exact likenesses from the three reference photos.The composition features all but one of the people sitting stiffly on a stool in the foreground, wearing a bulky, knitted ugly Christmas sweater with a reindeer pattern and high-waisted light-wash jeans. They are smiling uncomfortably at the camera. Above them in the upper corner, there is a large, translucent "floating head" double-exposure portrait of the last reference photo person. The floating head is looking off into the distance pensively, wearing a red turtleneck, fading into a cloudy, dark grey studio backdrop." "An incredibly awkward 90s studio photograph using the likenesses of reference photos of the family. The family is posed dynamically against a mottled green and red muslin backdrop. They are all wearing oversized, clashy holiday vests over turtlenecks. One family member is kneeling on the grey carpet floor, holding up a cheap, plastic illuminated snowman lawn ornament as if it is a treasure. The other family members are crowded around behind them, pointing at the plastic snowman with overly exaggerated, fake expressions of surprise and delight (mouths open, pointing fingers stiff). One person has a mullet hairstyle."
Partner @a16z AI 🤖 and twin to @omooretweets | Investor in @elevenlabsio, @krea_ai, @bfl_ml, @hedra_labs, @wabi, @WaveFormsAI, @ViggleAI, @MireloAI
it’s kinda hilarious that the infra pattern for agents is durable execution and serverless sandboxes
leading deepagents and building evals @LangChainAI, prev @awscloud, phd cs @ temple
阿里给Qwen-Image做了大升级，角色一致性增强、多人更稳、自带LoRA特效，新增几何推理能力 从效果看一致性很强，单人肖像编辑不变脸，两张人像合成的效果保真度比较高，五官、光影、风格能对的齐 内置LoRA，打光、新视角等等这些常用的效果不用再额外装模型了，用它直接出图 工业设计场景上，可以批量生成产品外观，一键换材质 新增的几何推理能力，模型可以直接生成辅助线效果 #AI图像生成 #QwenImage
模型：https://t.co/HtyxB5Hpp6 HF：https://t.co/WC8HitFJgh
btw, Russian sweets are pretty good and deserve more recognition. A tasteful mix of European and Asian tradition. Pastila, zefir, even barbaris candy. Arguably better with tea than British classics, devastates "labubu chocolate" or whatever that hype was. I miss it.
We're in a race. It's not USA vs China but humans and AGIs vs ape power centralization. @deepseek_ai stan #1, 2023–Deep Time «C’est la guerre.» ®1
RT @marclou: 2025 Usage Bill: $3,220 That's 1/3 of a SWE salary. I ship 3x faster with AI. This is the greatest time to be alive. https:…
💻 https://t.co/Y30jsaHwz9 $30K/m ⚡️ https://t.co/vatLDmi9UG $21K/m 📈 https://t.co/3EDxln5mdi $17K/m ⭐️ https://t.co/MZc8tG9xWi $17K/m 🍜 https://t.co/r07EpGSYJ2 $1K/m 🧬 https://t.co/SfrVXVtmdA $0/m 🧾 https://t.co/7olaOzV8Xd $0/m +20 https://t.co/4zCWHGJp1S
RT @yan5xu: @dotey skills 重点在Prompt 发现&懒加载，改变当前 agent 能力，有当前完整上下文，我觉得适合的场景是当前任务复合程度不高的情况（载入多个 skills 就会出现性能下降问题），比如主 Agent 是入口当做路由，然后通过 ski…
Prompt Engineer, dedicated to learning and disseminating knowledge about AI, software engineering, and engineering management.