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
540
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
540
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
340
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
20261017福岡devIO 「AIは"良いダッシュボード"を作れるか?
jtakeda
0
190
会社説明資料
persolserverworks
0
9.8k
エンタメ企業のM&Aを支えるデータ基盤 ― 統合から店舗のリアルタイム分析まで / Data Engineering Summit 2026
genda
0
190
触りたくないデータに、どう触るか AI時代のRBACアクセスガバナンス
ivry_presentationmaterials
0
280
宣言型部分更新は何を解決しどこへ向かうのか
shuta13
1
470
古い指輪から広がった JAVA コミュニティ とのつながり
yamad
0
130
しろおびから始める!ログ活用の第一歩
shumei_ito
0
960
「Docker Desktop不要の時代」は 来たのか?
ueponx
0
830
FinOps Agentが生んだ技術負債:コスト自動調査の落とし穴と解消までの道のり
oasis1994liveforever
2
140
夫婦で子育てするための育児標準化
codmoninc
PRO
0
450
Getting Started with Google Antigravity
glaforge
0
320
JAWSUG TOHOKU 青森支部 「LoGoチャット」のAWS移行で 乗り越えたこと
taketakekaho
0
340
Featured
See All Featured
Six Lessons from altMBA
skipperchong
29
4.5k
[Rails World 2026] Durable orchestration on Rails: from continuation to workflow
palkan
1
750
[RailsConf 2023] Rails as a piece of cake
palkan
59
7.1k
Jess Joyce - The Pitfalls of Following Frameworks
techseoconnect
PRO
1
450
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.5k
Crafting Experiences
bethany
1
380
The Impact of AI in SEO - AI Overviews June 2024 Edition
aleyda
6
1.2k
Designing Experiences People Love
moore
143
24k
Automating Front-end Workflow
addyosmani
1369
210k
GitHub's CSS Performance
jonrohan
1033
470k
Between Models and Reality
mayunak
4
500
Visual Storytelling: How to be a Superhuman Communicator
reverentgeek
2
710
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