Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
20230322 - Generative AI 小聚 ft. Happy Designer
Search
蒼時弦や
March 22, 2023
Technology
510
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
20230322 - Generative AI 小聚 ft. Happy Designer
TLDR
蒼時弦や
March 22, 2023
More Decks by 蒼時弦や
See All by 蒼時弦や
2024 - COSCUP - Clean Architecture in Rails
elct9620
2
240
2023 - RubyConfTW - Rethink Rails Architecture
elct9620
0
300
20230916 - DDDTW - 導入 Domain-Driven Design 的最佳時機
elct9620
0
530
2023 - WebConf - 選擇適合你的技能組合
elct9620
0
760
2022 - 默默會 - 重新學習 MVC 的 Model
elct9620
1
530
MOPCON 2022 - 從 Domain-Driven Design 看網站開發框架隱藏
elct9620
1
550
2022 - COSCUP - 我想慢慢寫程式該怎麼辦?
elct9620
0
330
2022 - COSCUP - 打造高速 Ruby 專案開發流程
elct9620
0
380
2021 - RubyKaigi - It is time to build your mruby VM on the microcontroller?
elct9620
0
330
Other Decks in Technology
See All in Technology
Execution in the Kingdom of Agents: Reflections on Abstraction and Complexity
bcantrill
0
900
AI駆動開発の時代になったのでトヨタ生産方式から見直す
terurou
6
5.7k
AI時代のAPI開発を加速する品質ガードレール / API Quality Guardrails in the AI Era
yokawasa
0
180
Snapshot Testing in Practice: Predictable and Reliable SwiftUI Views
fespinoza
0
180
OR学会2026年秋期大会_機械学習と数理最適化の融合による、配合レシピ最適化システム開発事例
brainpadpr
0
120
会社説明資料
persolserverworks
0
9.7k
AI時代に必要な脅威モデリング― 変化の速度に負けない理解とリスク判断
masakane55
5
1.2k
不可逆な意思決定を避けながら10億超の顧客データを AI Ready にするデータ基盤設計
baseballyama
1
270
AIがコードを書く時代に、エンジニアは何で自分の価値を証明するのか / In an era where AI writes code how do engineers prove their value
carta_engineering
1
770
オンラインゲームのシステム全体像 - コロプラ 2026年度 新卒研修
colopl
0
1.1k
Jetson Orin Nanoとk3sとローカルLLMで音声文字起こしシステム作ってみた
y_sera15
0
110
OpenSharing について熱く語る〜AI アセットの共有について〜
kameitomohiro
0
250
Featured
See All Featured
The Curious Case for Waylosing
cassininazir
1
560
Scaling GitHub
holman
464
140k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
17k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
123
22k
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
inesmontani
PRO
3
2.4k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
31
2.9k
Utilizing Notion as your number one productivity tool
mfonobong
4
610
How to Grow Your eCommerce with AI & Automation
katarinadahlin
PRO
2
320
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
35
2.6k
Darren the Foodie - Storyboard
khoart
PRO
4
4k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.9k
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
1.5k
Transcript
除了串 API 之外工程師還能做些什麼 Generative AI Meetup ft. Happy Designer
蒼時弦也 Software Developer https://blog.aotoki.me
開始之前 生態系進化太快,都不知道該怎麼辦⋯⋯
Diffusers 簡單使用 Stable Diffusion 的方法
Hugging Face AI 領域的 GitHub,大部分開源模型都可以在上面找到
import from import = = = = = torch diffusers
StableDiffusionPipeline pipe StableDiffusionPipeline.from_pretrained( , torch.float16) pipe pipe.to( ) prompt image pipe(prompt).images[ ] # 載入模型 # 進行運算 "runwayml/stable- diffusion-v1-5" "cuda" "a photo of an astronaut riding a horse on mars" torch_dtype 0
# ... # 載入不同模型 # 多重處理 prompt image txt2image(prompt).images[ ]
image upscale(image).images[ ] image image2image(image).images[ ] = = = = "a photo of an astronaut riding a horse on mars" 0 0 0
None
http://bit.ly/3JJf16o
Replicate 目前最好用的 Serverless GPU 服務
None
from import import class def def = = = =
= return cog BasePredictor, Path, Input torch ( ): (self): (self, image: Path Input( ), scale: Input( , ) ) -> Path: output Predictor BasePredictor setup predict # 初始化、載入模型 # 處理 e.g. Stable Diffusion Pipeline description description default "Image to enlarge" "Factor to scale image by" float 1.5
$ $ cog login cog push r8.im your username your
model name /< - >/< - - >
有 GPU 的伺服器、API 都有了,剩下就是套應用
AI Gacha 使用 Diffusers、Replicate 的實驗性專案
None
http://bit.ly/3yImmgc
我的看法 能做的事情其實不多,大部分應用的成本也偏高,但是商用已經沒 有問題,剩下要處理的大概會在 跟讓更多人能 合法的版權 輕鬆上手