Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
20230322 - Generative AI 小聚 ft. Happy Designer
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
蒼時弦や
March 22, 2023
Technology
470
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
210
2023 - RubyConfTW - Rethink Rails Architecture
elct9620
0
250
20230916 - DDDTW - 導入 Domain-Driven Design 的最佳時機
elct9620
0
480
2023 - WebConf - 選擇適合你的技能組合
elct9620
0
700
2022 - 默默會 - 重新學習 MVC 的 Model
elct9620
1
510
MOPCON 2022 - 從 Domain-Driven Design 看網站開發框架隱藏
elct9620
1
540
2022 - COSCUP - 我想慢慢寫程式該怎麼辦?
elct9620
0
300
2022 - COSCUP - 打造高速 Ruby 專案開發流程
elct9620
0
340
2021 - RubyKaigi - It is time to build your mruby VM on the microcontroller?
elct9620
0
310
Other Decks in Technology
See All in Technology
PostgreSQL 19 新機能概要 OSC Hokkaido 2026
nori_shinoda
0
250
AIはどのように 組織のアジリティを変えるのか?
junki
4
1.4k
時期が悪い!それでもRaspberry Piを買って遊んで活用するには / 20260627-osc26do-rpi-jikigawarui
akkiesoft
0
830
飲食店もAIで。レジ締めやハンディシステムをつくってる話 / Using AI for restaurant management
vtryo
0
180
AIをフル活用してオンコール機能のプロトタイプを2日で作った話 / Building an AI-Powered On-Call Prototype in Just Two Days
nari_ex
0
140
AIネイティブな開発のサプライチェーンリスク対策 〜激動の開発現場でリスクに立ち向かう〜【ZennFes】
cscengineer
PRO
2
160
AIチャットの改善から見えた、良いAI体験とは / What Constitutes a Good AI Experience: Insights from Improving AI Chat
kubode
0
120
【2026年版】 ベクトル検索とEmbedding最前線
mocobeta
24
7.6k
MySQL & MySQL HeatWave Report - June 2026
freshdaz
0
150
クレデンシャル流出 ― 攻撃 3 時間 vs 復旧 10 時間。この非対称性にどう備えるか
kazzpapa3
3
570
FPC(フレキシブル)基板にZephyr実装してみた。
iotengineer22
0
170
2026 AI Memory Architecture
nagatsu
0
330
Featured
See All Featured
ラッコキーワード サービス紹介資料
rakko
1
3.7M
Noah Learner - AI + Me: how we built a GSC Bulk Export data pipeline
techseoconnect
PRO
0
200
Stewardship and Sustainability of Urban and Community Forests
pwiseman
0
230
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
620
Thoughts on Productivity
jonyablonski
76
5.2k
Odyssey Design
rkendrick25
PRO
2
710
Groundhog Day: Seeking Process in Gaming for Health
codingconduct
0
220
Between Models and Reality
mayunak
4
350
Bridging the Design Gap: How Collaborative Modelling removes blockers to flow between stakeholders and teams @FastFlow conf
baasie
0
590
Art, The Web, and Tiny UX
lynnandtonic
304
22k
30 Presentation Tips
portentint
PRO
1
330
WENDY [Excerpt]
tessaabrams
11
38k
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