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
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
240
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
690
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
330
2021 - RubyKaigi - It is time to build your mruby VM on the microcontroller?
elct9620
0
300
Other Decks in Technology
See All in Technology
On-behalf-of Token exchange with AgentCore Identity
hironobuiga
2
140
10倍の生産性を実現するAI駆動並列エージェントのすべて
kumaiu
5
1.3k
Dario Amodi『Policy on the AI Exponential』を理解する
nagatsu
0
220
Disciplined Vibes: Scaling AI-Assisted Engineering
sheharyar
0
130
RSA暗号を手計算したくなること、ありますよね?? (20260615_orestudy6_rsa)
thousanda
0
210
SIer20年! 培ったスキルがスタートアップで輝く時
shucho0103
0
830
Bucharest Tech Week 2026 - Reinventing testing practices in the AI era
edeandrea
PRO
1
140
「速く作る」から「正しく作る」へ ─ 生成AI時代の開発フロー改革の ロードマップと実行 ─
starfish719
0
9.8k
How Timee Delivers Day 1 Production Ready LLM Features
tomoyks
0
120
protovalidate-es を導入してみた
bengo4com
0
170
Oracle AI Database@Azure:サービス概要のご紹介
oracle4engineer
PRO
6
1.9k
日本 Fintech 未来予測レポート 2027〜2028年(手動編集版)
8maki
0
1.7k
Featured
See All Featured
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
soudai
PRO
65
55k
エンジニアに許された特別な時間の終わり
watany
107
250k
Sam Torres - BigQuery for SEOs
techseoconnect
PRO
0
280
Beyond borders and beyond the search box: How to win the global "messy middle" with AI-driven SEO
davidcarrasco
3
150
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
128
56k
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
1.3k
Stop Working from a Prison Cell
hatefulcrawdad
274
21k
Efficient Content Optimization with Google Search Console & Apps Script
katarinadahlin
PRO
1
610
Reality Check: Gamification 10 Years Later
codingconduct
0
2.2k
Reflections from 52 weeks, 52 projects
jeffersonlam
356
21k
Building Experiences: Design Systems, User Experience, and Full Site Editing
marktimemedia
0
530
A Tale of Four Properties
chriscoyier
163
24k
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