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
520
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
270
2023 - RubyConfTW - Rethink Rails Architecture
elct9620
0
320
20230916 - DDDTW - 導入 Domain-Driven Design 的最佳時機
elct9620
0
550
2023 - WebConf - 選擇適合你的技能組合
elct9620
0
780
2022 - 默默會 - 重新學習 MVC 的 Model
elct9620
1
550
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
350
2022 - COSCUP - 打造高速 Ruby 專案開發流程
elct9620
0
390
2021 - RubyKaigi - It is time to build your mruby VM on the microcontroller?
elct9620
0
340
Other Decks in Technology
See All in Technology
Claude Codeで作ったアプリを安全に公開する/Built with Claude Japan 2026
yoshidashingo
0
210
Agent Harnessはどう作る?事例から学ぶAI Agentの設計思想
sergicalsix
0
160
バックオフィスに染み出すTypeScript ── clasp で安全に仕組みを作る
nealle
1
180
bpf_arenaとstruct_opsを使うのが難しかった話
masu_mi
0
210
並列度を下げたら速くなった — go build の重複コンパイルを実測で見る
tomoaki25
2
960
FinOpsを導入してマルチプロダクトのコスト最適化を実現する
kworkdev
PRO
0
140
Context Ontology Accelerator 入門 (業務データの意味を、AI エージェントに渡す)
inariku
PRO
3
570
「いつか使う」の「いつか」は来ない 〜AI駆動開発における「作らない」判断について〜
ikki0006
0
170
Active Directory と Entra ID のむむむな関係
murachiakira
PRO
3
1.7k
Shared Signals Framework 仕様解説
oidfj
0
260
Metadata - Section 3 : Dublin Core Standard · DC
mohab1
0
120
自治体AIコンタクトセンター、何をどこに任せる?~Amazon Connect Customer +Amazon Bedrockの実践知~ / 20261107 Satoshi Torano
shift_evolve
PRO
1
110
Featured
See All Featured
The State of eCommerce SEO: How to Win in Today's Products SERPs - #SEOweek
aleyda
2
12k
Lightning Talk: Beautiful Slides for Beginners
inesmontani
PRO
2
760
Facilitating Awesome Meetings
lara
57
7.2k
How Software Deployment tools have changed in the past 20 years
geshan
3
35k
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
4
4.4k
The Anti-SEO Checklist Checklist. Pubcon Cyber Week
ryanjones
0
290
Highjacked: Video Game Concept Design
rkendrick25
PRO
1
550
It's Worth the Effort
3n
188
29k
The Curious Case for Waylosing
cassininazir
1
610
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
370
Bootstrapping a Software Product
garrettdimon
PRO
306
120k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
46
3.1k
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