工具狂

384 posts

工具狂 banner
工具狂

工具狂

@crazytoolman

每天一款实用工具，让效率起飞！

Hubei Katılım Aralık 2011
816 Takip Edilen47 Takipçiler
工具狂 retweetledi
Demis Hassabis
Demis Hassabis@demishassabis·
Gemini 3.5 Flash is amazing! - Performs better than 3.1 Pro on coding & agentic tasks - 4x faster than other frontier models - 12x faster in @antigravity - 800 tokens/sec! - Often at less than half the cost And Pro to come… Try it in @antigravity, @GeminiApp & more - enjoy!
Demis Hassabis tweet media
English
164
149
2.1K
82K
工具狂
工具狂@crazytoolman·
用在 ZiT上比用在Z-image Base上效果好。
Draw Things@drawthingsapp

🔍 An interesting discovery! 🧩 Z-Image-Fun-Lora-Distill from alibaba-pai was originally trained for Z-Image Base, with 2-step, 4-step, and 8-step versions available. ⚡ But during some accidental testing in Draw Things, We found that Z Image Turbo paired with Z-Image-Fun-Lora-Distill delivers surprisingly excellent results, as shown in the comparison images below. 🚀 It can even reduce ZiT generation from 8–9 steps down to just 3–4 steps, which greatly shortens local generation time! 👇🏻 The comments include detailed generation settings and the LoRA link for reference.

中文
0
0
0
25
工具狂
工具狂@crazytoolman·
@seeker_wealth @drawthingsapp I tested it for you — illustration, anime, and cartoon styles all work. But you do need to adjust the prompt accordingly.
工具狂 tweet media
English
1
0
2
86
Rohit T
Rohit T@seeker_wealth·
@drawthingsapp Only work with realistic images or illustrations as well?
English
1
0
0
626
Draw Things
Draw Things@drawthingsapp·
🚨 Another Super Great Ultimate Upscaler LoRA！ ✨ Elevate your Low-Quality or Blurry images with 4-step generation——Designed to inject high-frequency textures and erase compression artifacts for professional-grade photorealism. 🧪 This is a LoRA for Flux.2 Klein 9B, and the results tested in Draw Things are excellent! 👇🏻 Click the comments for the LoRA link, detailed information, and recommended settings!
Draw Things tweet mediaDraw Things tweet mediaDraw Things tweet mediaDraw Things tweet media
English
6
17
180
11.6K
工具狂
工具狂@crazytoolman·
效果很好！
Draw Things@drawthingsapp

🚨 Another Super Great Ultimate Upscaler LoRA！ ✨ Elevate your Low-Quality or Blurry images with 4-step generation——Designed to inject high-frequency textures and erase compression artifacts for professional-grade photorealism. 🧪 This is a LoRA for Flux.2 Klein 9B, and the results tested in Draw Things are excellent! 👇🏻 Click the comments for the LoRA link, detailed information, and recommended settings!

日本語
0
0
0
29
工具狂 retweetledi
OpenAI
OpenAI@OpenAI·
If a task needs multiple tools, Codex chooses the best one for each step. It uses plugins when they can handle the job, Chrome when it needs a logged-in website, and combines approaches as needed.
English
27
41
727
170.4K
比特币橙子Trader
比特币橙子Trader@oragnes·
你每天用的谷歌Chrome浏览器，居然在后台悄悄给你塞了个4GB的AI大模型！零通知、零授权，自动下载Gemini Nano。 它把你电脑当算力节点跑诈骗检测，删了还会自动重下。 谷歌Chrome浏览器开始在后台自动向符合硬件条件的用户设备下载体积约4GB的Gemini Nano人工智能模型文件。 该下载行为未提供前置授权弹窗或明确的存储空间预警，并在用户手动删除后自动重新下载，引发安全研究员与用户对终端控制权及资源消耗的争议。 该核心文件名为“weights.bin”，存放于用户系统目录的OptGuideOnDeviceModel文件夹中。 据测试，在无用户交互的情况下，后台下载及部署过程约耗时14分钟。 Chrome利用该本地大语言模型驱动“辅助写作”、端侧诈骗检测与网页总结等默认开启的AI功能。 用户若需彻底阻止该模型下载，必须进入开发者面板，手动禁用“优化指南端侧模型”与“Prompt API”，并清理本地残留目录。 方法：想彻底禁用并删除： 1.打开chrome://flags 搜索并禁用以下两项： optimization-guide-on-device-model（设为Disabled） prompt-api-for-gemini-nano（或相关Prompt API，设为Disabled） 2.重启Chrome 3.手动删除文件夹： Windows：%LOCALAPPDATA%\Google\Chrome\User Data\OptGuideOnDeviceModel Mac：~/Library/Application Support/Google/Chrome/User Data/OptGuideOnDeviceModel 建议同时在Chrome设置里关闭所有AI实验功能。
中文
81
133
661
148.7K
Sveinbjorn
Sveinbjorn@sveinbjornp·
@drawthingsapp can it realistically process video or is it just fast enough for photos?
English
1
0
0
190
Draw Things
Draw Things@drawthingsapp·
🔍 SeedVR2 is now officially supported in Draw Things! 🔄 Please update to the latest version v1.20260430.0 in the iOS / macOS AppStore. This version brings: 🔹Support SeedVR2 as one of the diffusion models for 1-step upscaling work.（Check the comments for SeedVR2 DT parameters.） 🔹Fix Anima LLM adapter related issues. 🔹Switch to better and newer causal / mask attention kernels. 🔹Support export LoRAs for Qwen, Z Image, FLUX.2 and ERNIE Image models. 🔹Imported Z Image models now run at BF16 precision. gRPCServerCLI and draw-things-cli both are updated to 1.20260430.0 with above related updates.
Draw Things tweet media
English
3
3
32
3.7K
工具狂
工具狂@crazytoolman·
效果出色，非常好的放大模型，目前在模型列表中可用，只需1步放大。
Draw Things@drawthingsapp

🔍 SeedVR2 is now officially supported in Draw Things! 🔄 Please update to the latest version v1.20260430.0 in the iOS / macOS AppStore. This version brings: 🔹Support SeedVR2 as one of the diffusion models for 1-step upscaling work.（Check the comments for SeedVR2 DT parameters.） 🔹Fix Anima LLM adapter related issues. 🔹Switch to better and newer causal / mask attention kernels. 🔹Support export LoRAs for Qwen, Z Image, FLUX.2 and ERNIE Image models. 🔹Imported Z Image models now run at BF16 precision. gRPCServerCLI and draw-things-cli both are updated to 1.20260430.0 with above related updates.

中文
0
0
0
53
ERNIE for Developers
ERNIE for Developers@ErnieforDevs·
Introducing ERNIE 5.1 Preview — now live! 🚀 Ranked #13 globally and #1 among Chinese labs on @arena 's Text Arena. Top-10 worldwide across: 📐 Math — #9 ⚖️ Legal & Government — #1 💼 Business, Management & Financial Ops — #4 💻 Software & IT Services — #7 Built on the strong pre-training foundation of ERNIE 5.0, ERNIE 5.1 Preview compresses total parameters to ~1/3 and activated parameters to ~1/2 of its predecessor, while using only ~6% of the pre-training cost of comparable models — delivering leading foundational performance at its scale. Try it now 👉 ernie.baidu.com More new models are on the way — stay tuned 👀
ERNIE for Developers tweet media
English
45
58
409
125.6K
Draw Things
Draw Things@drawthingsapp·
🚨 Hidden Gem in Draw Things: Custom Built-in Prompts! 💡 Did you know you can create your own "Built-in prompts" in DT? 1️⃣Go to the Documents folder of Draw Things. 2️⃣Create a file named custom_prompts.txt 3️⃣Add your favorite prompts (one per line). 4️⃣Restart the app, and they’ll appear in the Project bar at the top! 🚀 Super handy for your go-to workflows. —————— 🛣️ Path: /Users/[Your Username]/Library/Containers/com.liuliu.draw-things/Data/Documents/ ——————
Draw Things tweet mediaDraw Things tweet media
English
5
6
47
9.9K
工具狂
工具狂@crazytoolman·
@crifytosp @drawthingsapp It's here, you can creat the custom_prompts.txt your own, the app will recognize it and replace the built -n prompts with this!
工具狂 tweet media
English
1
0
1
44
Draw Things
Draw Things@drawthingsapp·
📸 One Prompt to Remove The JPEG Artifacts feel of your images. 📝 You need to put this in your “custom_prompts.txt”: 🔧 We often encounter real-world or AI-generated images with obvious compression artifacts or banding. By using Flux.2 Klein 9B KV paired with the following prompt, you can effectively remove these imperfections while keeping everything else intact.
Draw Things tweet media
Draw Things@drawthingsapp

🚨 Hidden Gem in Draw Things: Custom Built-in Prompts! 💡 Did you know you can create your own "Built-in prompts" in DT? 1️⃣Go to the Documents folder of Draw Things. 2️⃣Create a file named custom_prompts.txt 3️⃣Add your favorite prompts (one per line). 4️⃣Restart the app, and they’ll appear in the Project bar at the top! 🚀 Super handy for your go-to workflows. —————— 🛣️ Path: /Users/[Your Username]/Library/Containers/com.liuliu.draw-things/Data/Documents/ ——————

English
1
3
36
6.7K
Haoxing Chen
Haoxing Chen@Chenhaoxing249·
After two months of teamwork, we’re excited to share our team’s latest achievement — LLaDA2.0-Uni, InclusionAI’s first multimodal LLaDA. A unified discrete diffusion LLM built for both understanding and generation across text and images. Highlights: ● One paradigm for VQA, doc understanding, and image generation ● Efficient inference with a new decoding strategy + 8-step distilled decoder ● Interleaved text-image generation enabled by unified discrete representations (SGLang support soon) 🤗 Hugging Face: huggingface.co/inclusionAI/LL… 📷 ModelScope: modelscope.cn/models/inclusi…
Haoxing Chen tweet media
English
2
9
53
17.5K
工具狂
工具狂@crazytoolman·
一定要下载！百度文心图像Ernie Image正在席卷开源图像市场，这是正宗小香蕉！Draw Things已正式支持 ｜ 食用指南 youtu.be/_R2oKfvSHfc?si… 来自 @YouTube
YouTube video
YouTube
中文
0
0
0
122
工具狂
工具狂@crazytoolman·
抓紧更新啦！Ernie Image这是一次真正意义的小香蕉。8B输出这样的结果，impressive！
Draw Things@drawthingsapp

🚨 This update brings support for several awesome new models — GO UPDATE NOW! 🔄 Draw Things v1.20260418.1 was released on the iOS / macOS App Store a few hours ago: 1️⃣ Support for ERNIE Image, including LoRA import, training, and model import. @ErnieforDevs 2️⃣ Support for Anima Preview 3, including LoRA import, training, and model import. 3️⃣ Updated to LTX-2.3 [distilled] 1.1. 4️⃣ Fixed a crash related to Z-Image LoRA training. 5️⃣ Experimental ANE + NAX hybrid inference. gRPCServerCLI and draw-things-cli have both been updated to 1.20260418.1 with the above changes.

中文
0
0
0
92

Keşfet

@antigravity @GeminiApp @seeker_wealth @drawthingsapp @YouTube @oragnes @sveinbjornp @ErnieforDevs