40. 이미지 생성(출력) 활용

Video

준비 중

Note

생성된 이미지 저장 예시

stream 없이stream=True

• stream이 아닌 경우 이미지 생성 툴 옵션에서 Partial images를 None으로 설정해야 함.
  test.py

  import yaml
  from dotenv import load_dotenv
  from openai import OpenAI
  
  with open("config.yaml") as f:
      config = yaml.safe_load(f)
  
  load_dotenv()
  client = OpenAI()
  
  response = client.responses.create(
      input="고양이 이미지 생성해줘",
      **config
  )
  
  print("Assistant: ", response.output_text)
  
  import base64
  for output in response.output:
      if output.type == "image_generation_call":
          image_base64 = output.result
          image_format = output.output_format
          with open(f"test/output_image.{image_format}", "wb") as f:
              f.write(base64.b64decode(image_base64))
  

• 이미지 생성 툴 옵션에서 Partial images를 1 이상으로 설정해야 부분 이미지를 받을 수 있음.
  test.py

  import yaml
  from dotenv import load_dotenv
  from openai import OpenAI
  
  with open("config.yaml") as f:
      config = yaml.safe_load(f)
  
  load_dotenv()
  client = OpenAI()
  
  response = client.responses.create(
      input="고양이 이미지 생성해줘",
      stream=True,
      **config
  )
  
  print("Assistant: ", end="", flush=True)
  
  import base64
  for event in response:
      if event.type == "response.output_text.delta":
          print(event.delta, end="", flush=True)
      elif event.type == "response.completed":
          previous_response_id = event.response.id
      elif event.type == "response.image_generation_call.partial_image":
          image_base64 = event.partial_image_b64
          image_format = event.output_format
          with open(f"test/output_image.{image_format}", "wb") as f:
              f.write(base64.b64decode(image_base64))
  

---

Resources