cjzdaily
04:14 · Dec 23, 2025 · Tue
https://x.com/unslothai/status/2003098731852488864?s=12
X (formerly Twitter)
Unsloth AI (@UnslothAI) on X
NVIDIA made a beginner's guide to fine-tuning LLMs with Unsloth!
💚
You'll learn about:
- Training methods: LoRA, FFT, RL
- When to fine-tune and why + use-cases
- Amount of data and VRAM needed
- How to train locally on DGX Spark, RTX GPUs & more
Guide:…
04:44 · Dec 22, 2025 · Mon
https://x.com/pjaccetturo/status/2002777819903062060?s=12
X (formerly Twitter)
PJ Ace (@PJaccetturo) on X
Our $1,000,000 AI film festival submission
🚨
I took 6 top Hollywood cinematographers with ZERO AI experience and taught them a simple framework to master the tools.
You can easily learn this process in minutes
👇
Here are the exact tips, prompts, and framework…
22:17 · Dec 20, 2025 · Sat
https://x.com/petergyang/status/2002402550570758283?s=12
X (formerly Twitter)
Peter Yang (@petergyang) on X
All my practical Claude Code tutorials and interviews in one list:
TUTORIALS
Build a movie discovery app in 15 min:
https://t.co/yuPBfbJxsI
Build a YouTube research agent in 15 min:
https://t.co/LxIOm1sKTz
Build a family activity finder in 35 min: ht…
21:43 · Dec 20, 2025 · Sat
https://x.com/moyu_7777/status/2002218795382026567?s=12
X (formerly Twitter)
墨鱼(:◎)≡
♥
MemeMax
⚡️
(@MoYU_7777) on X
今天凡人修仙传更新 真是越来越好看了
14:40 · Dec 20, 2025 · Sat
https://x.com/azed_ai/status/2002046100350656622?s=12
X (formerly Twitter)
Amira Zairi (@azed_ai) on X
Higgsfield's Cinema Studio turns a single cinematic image into a full, flowing shot.
ARRI and Panavision style cameras, real film language, native 4K, all driven from one starting frame.
This is not image to video, this is frame to film, where a single…
18:36 · Dec 19, 2025 · Fri
https://x.com/morphic/status/2001721625226649717?s=12
X (formerly Twitter)
Morphic (@morphic) on X
3×3 grid → frame isolation → animation.
All inside @morphic.
This works insanely well for scenes with dialogues. Here’s how:
12:26 · Dec 16, 2025 · Tue
https://x.com/aigclink/status/2000840150084149606?s=12
X (formerly Twitter)
AIGCLINK (@aigclink) on X
强,阿里刚刚放出了:Wan 2.6,支持角色扮演,给一段人物视频+提示,可以自动完成分镜、表演、配音
就是说给出一段视频,它能保留角色人物、声音、动作,按提示词重新“演戏”
支持一次生成15秒视频
支持音画同步、声音驱动、多镜头自动切换
15:58 · Dec 15, 2025 · Mon
https://x.com/seekjourney/status/2000420492935925767?s=12
X (formerly Twitter)
极客杰尼 (@seekjourney) on X
发现一个超实用的 Prompt 收集站,一键复制即用,省时高效!
从油画到赛博朋克,从水彩到3D渲染 ,各种视觉风格应有尽有,找灵感二次创作非常适合。
👉
https://t.co/1iPCxJTVTo
12:08 · Dec 15, 2025 · Mon
https://x.com/pluvio9yte/status/2000228121467904054?s=12
X (formerly Twitter)
雪踏乌云 (@Pluvio9yte) on X
推荐一个汇总了 Claude Code Skills 的仓库。
覆盖了开发、测试、工作流、安全等一系列skills。
可以即插即用也能自己魔改。
链接在评论区。
12:08 · Dec 15, 2025 · Mon
https://x.com/dynamicwangs/status/1999142428268507583?s=12
X (formerly Twitter)
DynamicWang (@dynamicwangs) on X
AWPortrait Z 即将在本周于HF和Liblib发布
代号Z代表了基于 Zimage 底模深度定制的人像美学增强包(LoRA)。
1. 针对 Zimage 原生噪点过多的问题进行了修正,修正原模型皮肤普遍自带类绒毛的高频噪声信息,让看起来既真实又完美。
2.
12:07 · Dec 15, 2025 · Mon
https://huggingface.co/Shakker-Labs/AWPortrait-Z
09:35 · Dec 15, 2025 · Mon
https://x.com/miantiao_me/status/2000166814379106687?s=12
X (formerly Twitter)
面条 (@miantiao_me) on X
这个 Design Prompts 网站真不错,里边有 30+ 常见网页设计风格,提供了 Agent 的 Prompt。
放到 Claude Code 的 Subagent 中,就可以让这些 AI 网页设计师快速为你的网站生成美观统一的界面了。
07:46 · Dec 15, 2025 · Mon
https://x.com/ttmouse/status/2000244570253324427?s=12
X (formerly Twitter)
ttmouse (@ttmouse) on X
🍌
Nano Banana Pro prompt 精选帖子格式化
(13-14日高赞版)
以下是将您提供的链接转换为标准热帖监控格式的版本。每条基于实际帖子内容,提取一句话描述、互动数据(最新获取)、发布时间和链接。部分为模糊识别(非显式关键词但明显Nano Banana Pro作品)。
近期减少了纯人像相关的内容。
```
16:48 · Dec 12, 2025 · Fri
https://x.com/op7418/status/1999491858662326281?s=12
16:46 · Dec 12, 2025 · Fri
https://x.com/vikingmute/status/1999467938353676341?s=12
X (formerly Twitter)
Viking (@vikingmute) on X
发现一个非常棒的 shadcn/ui 的主题站点:https://t.co/ENPUjpYH14
主题非常多,有官方的,社区自制的,tweakcn 的,还有 rayso 的。下载这些主题都是免费的。
比之前我一直在用的 https://t.co/NnKOTvd88i 还要多很多
这个站点的野心,其实不止是 shadcn 的主题,而是可以让 AI
13:49 · Dec 12, 2025 · Fri
https://x.com/fhwofjow51260/status/1999471317909930043?s=12
13:37 · Dec 12, 2025 · Fri
https://x.com/joshesye/status/1999126853039337840?s=12
23:47 · Dec 11, 2025 · Thu
https://x.com/yaohui12138/status/1998941539033395246?s=12
X (formerly Twitter)
超级个体|柿子 (@yaohui12138) on X
光会用还不够,notebooklm的六个神级提示词助力你的每个场景!
1.创意脑暴
从来源中脑暴10个创新想法:每个想法都要说明概念、对应证据、可行性评分(1-10分)、原型建议。鼓励疯狂类比和“如果……会怎样”的假设,最后按影响力排序。用轻松的对话方式回应,并基于我的回复继续发散。
23:46 · Dec 11, 2025 · Thu
https://x.com/xingpt/status/1999070830626742625?s=12
X (formerly Twitter)
XinGPT
🐶
(@xingpt) on X
【Vibe Coding 实战 Part 2】我用 AI 把“美股看板”升级并发布到了云端,全程只用了三步
在上一篇文章中,我们通过 Google Antigravity 和几句提示词,成功在本地电脑上跑出了一个简易的“美股追踪看板”。
但作为一个追求极致效率的 Vibe
23:45 · Dec 11, 2025 · Thu
https://x.com/wildmindai/status/1998701673158685094?s=12
X (formerly Twitter)
Wildminder (@wildmindai) on X
As usual, Kijai has prepared the Wan-Move, and it is available in ComfyUI.
https://t.co/zVQnJz0YPy
Before
After
Home
Powered by
BroadcastChannel
&
Sepia