Cuestionario vinculado a una guía · Medio Nivel
Generadores de imágenes de IA en el cuestionario de clase de arte
Prueba cómo los modelos de difusión crean imágenes, la decisión de derechos de autor de Zarya of the Dawn y las prácticas de atribución y seguridad para la clase de arte.
Pregunta 1 de 8
¿Cómo crea un modelo de difusión una imagen a partir de un mensaje?
Vista previa de cada pregunta8 preguntas
Las respuestas y explicaciones aparecen a medida que realiza el cuestionario.
- ¿Cómo crea un modelo de difusión una imagen a partir de un mensaje?
- It starts from random noise and refines it step by step into an image that matches the text
- It searches the web and returns the closest photo
- It cuts and pastes pieces of stored images together
- It traces over an image the user uploads
- ¿Qué decidió la Oficina de Derechos de Autor de EE. UU. sobre 'Zarya of the Dawn' en 2023?
- The whole comic, including the images, was protected
- Nothing in the comic could be protected
- The text and arrangement were protected, but the individual Midjourney images were not
- Only the Midjourney images were protected
- ¿En qué dice Adobe que está entrenado Firefly?
- Only images scraped from social media
- Licensed content such as Adobe Stock, plus public domain material
- Students' uploaded artwork
- Nothing; it has no training data
- ¿Qué controla la semilla aleatoria en la generación de imágenes?
- The colour palette
- El tamaño del archivo de la imagen.
- Which tool is used
- The starting noise, so the same prompt and seed usually produce the same image again
- ¿Por qué la guía dice que los modos de imagen a imagen suelen adaptarse bien al aula?
- They keep more of the student's own composition
- siempre son gratis
- They never show bias
- They need no prompt at all
- Which statement corrects a common misconception about image generators?
- They store every training image and paste them together
- They cannot produce anything resembling their training data
- They learn statistical patterns, though they can sometimes produce close copies of images that appeared many times in training
- They only produce abstract art
- What attribution practice does the guide recommend for AI-assisted student work?
- Hide AI use to keep grading fair
- Label the work, name the tool, keep the prompts, and describe what the student changed
- Credit only the AI company
- Attribution is only needed for professional artists
- What does the guidance scale setting control?
- The age limit for users
- How many images are produced at once
- The image's resolution
- How closely the image follows the prompt versus how natural it looks