Función de Visión por IA – Describir Imagen a Texto
AI Vision is the feature to describe an image and convert the image to a prompt. It’s done by using one of the popular IA models such ChatGpt or Gemini. You can select the model you prefer, based on the performance or the cost.

Descargar Light Image Editor
Descargar e instalar Redimensionador de imagen ligera 7
Ubica Light Image Editor en el icono de la bandeja, carga una imagen y ejecútalo desde el menú principal – Herramientas – IA Vision.

Obtener clave API
La función de inteligencia artificial AI Vision está disponible por ahora en la aplicación Light Image Editor, que viene incluida en el paquete de instalación de Light Image Resizer. Es una aplicación local solo para Windows. Necesitará una clave API , ya sea para Google Gemini o ChatGPT de OpenAI. Significa que pagarás sobre la marcha, sin necesidad de una suscripción mensual.
Primero, obtén la clave API de los modelos de visión
Obtén la clave API para Google AI Studio (Gemini)
Obtén la clave API de OpenAI (ChatGPT)
Por ahora, recomendamos usar Gemini, más barato y funciona bien para describir imágenes.
Una vez que tengas la clave (y los créditos), puede ingresar la clave en la opción de visión Light Image Resizer AI disponible en este menú.
The LLM vision models works fine in english, french, german, and popular languages, which is not the case of some other popular vision models, Ollama could be supported later if you find it interesting, and the big advantage means the data will be full private and local, and you won’t be charged for any requests and tokens. Consulta los modelos de visión compatibles con Ollama
Disclaimer: Be careful, even if you are running a local application on windows, the app resizes and sends the image to the cloud, if you don’t want to share your pictures or sensitive data (especially NSFW content) don’t use the cloud models.
¿Por qué describir tus imágenes?
Encontrar las palabras adecuadas para tus imágenes es fácil con la función de Visión por IA de Light Image Resizer. Función de Visión por IA En Light Image Editor. Analiza tus imágenes a nivel técnico para generar descripciones automáticamente. La aplicación prepara tu imagen (convirtiéndola a JPEG y ajustando el tamaño a algo como 1024×1024, que es ajustable) para un procesamiento eficiente de IA. Este paso de preanálisis ayuda a asegurar un procesamiento más rápido y puede hacer que la función sea más rentable. ¡Deja que la IA haga la descripción para que tú no tengas que hacerlo!

¿Qué tipo de tareas puedes completar?
Annotate your images to find them by keywords. Geoguessing the picture when you don’t remember where you took them. Find inspiration when you want to publish a new Instagram or TikTok post. It will add some nice icons to make your marketing better.
Todo depende de tu indicación, mira algunos ejemplos de indicaciones y cómo afectan al resultado.
Una vez que tengas la clave (y los créditos), puede ingresar la clave en la opción de visión Light Image Resizer AI disponible en este menú.
The LLM vision models work fine in English, French, German, and popular languages, which is not the case of some other popular vision models. Ollama could be supported later if you find it interesting, and the big advantage is that the data will be completely private and local, and you won’t be charged for any requests and tokens. Consulta los modelos de visión compatibles con Ollama
¿Cuál es la diferencia entre describir una imagen, analizar una imagen y resumir una imagen?
Y podría ser la misma pregunta sobre la diferencia entre una imagen, una fotografía y una foto. Es algo similar, pero depende de lo que necesites hacer y de quién seas. Mira algunas tareas posibles de Visión Artificial:
- Encontrar palabras clave para fotógrafos
- OCR y resumir documentos para contadores
- Subtitular imágenes automáticamente
- Inspiración para publicaciones en Instagram o TikTok
- Identificar marcas y celebridades
- Comercio electrónico de moda
- Geoconocimiento – Encontrar la ubicación a partir de la foto
- Diagnóstico científico, de salud, astronomía
Algunas ideas de prompts para describir una imagen
Palabras clave para fotografía
Devuelve directamente sin comentario una lista de 50 palabras clave separadas por comas para describir el sujeto, el fondo, los objetos, la ubicación y el estado de ánimo
Woman, convertible, car, desert, camels, sand, road, travel, tourism, adventure, vacation, stylish, fashion, portrait, outdoors, sunny, wind, hair, red hair, scarf, white car, leather seats, headrest, dry landscape, arid, heat, sunlight, model, posing, confident, relaxed, tourist attraction, horizon, background, faraway, blurred, out of focus, transport, open-top, leisure, wanderlust, modern, trendy, vogue, stylish, elegance, freedom, journey, explorer, remote, scenic, destination, casual, summer, daytime, vacation, escape, adventure, travel, road trip.
Resumen de documentos de la OCR
Realice un OCR detallado del documento, luego traduzca al inglés y explique en un resumen de 200 palabras qué es el documento y sus elementos importantes.
Este documento es una factura de “Les Minotiers,” a hotel/lodging (Logis de France) located in Mirepoix, France. The invoice, numbered 43197 and dated February 18, 2014, details the charges for a stay in Room 12. The guest arrived on February 17, 2014, and departed on February 18, 2014. The total amount due is 73.92 Euros. The charges include the room rate (57.00 Euros), tourist tax (0.92 Euros) and breakfast (16.00 Euros). The invoice breaks down the VAT (Value Added Tax) applied at 10% to a portion of the charges. The invoice also mentions an equivalent value of 484.88 in old french currency “Francos”. La información de contacto de la empresa, los identificadores comerciales y el IVA
Descripción de Instagram
Crea una descripción para una publicación de Instagram para un domingo, sé creativo y divertido para obtener la mejor interacción y número de 'me gusta' o comentarios
Sunday mood: plotting my next Parisian adventure. 🥐 This classic car + riverside views = 💯. But the real question is… champagne brunch or museum hop? 🤔 What’s YOUR ideal Sunday activity? Let me know in the comments! 👇 #ParisianVibes #SundayFunday #ClassicCars #StyleInspo #WeekendGetaway #TravelDreams
Ciencia & Educación
Como experto, analiza científicamente esta imagen y devuelve una descripción de 200 palabras. Sugiere la especialidad científica más adecuada para diagnosticar una solución.
This X-ray image depicts the bones of a human hand and wrist. The carpal bones, metacarpals, and phalanges are all visible. There appears to be a fracture of the proximal phalanx of the fourth digit (ring finger). The fracture appears to be a comminuted fracture, meaning the bone is broken into multiple fragments. There is visible displacement of the fractured bone fragments, indicating the fracture is not stable and may require intervention to ensure proper healing and alignment. No other obvious fractures or dislocations are apparent in the remaining bones of the hand and wrist in this particular projection. The bone density appears normal within the limits of this image.
The best scientific specialty to diagnose and determine a solution for this case is Orthopedic Surgery, specifically a hand specialist, who has the expertise to interpret the X-ray, assess the extent of the injury, and recommend the most appropriate treatment, which may involve immobilization with a cast or splint, or surgical intervention to realign and stabilize the fracture fragments. Radiologists are often consulted to ensure interpretation of x-rays.
Moda & comercio electrónico
Para una página de producto de comercio electrónico, describe la imagen con color, forma, materiales, estilo. Descripción de 100 palabras con impacto en marketing.
Dare to be different in this stunning black dress. Crafted from a soft, body-hugging knit, this piece features a sophisticated turtleneck and a figure-flattering silhouette that falls to a chic midi length. The drama lies in the voluminous, faux-fur cuffs, adding a touch of opulent texture and undeniable edge. Perfect for a night out or a statement-making event, this dress is a modern masterpiece. Effortlessly chic and endlessly versatile, prepare to turn heads wherever you go. Own the room. Own your style.
GeoAdivinación
Adivina la ubicación de la imagen, comienza con el país, luego la región y finalmente la ciudad. Agrega 50 palabras para describir el sujeto. Termina con un porcentaje de estimación de precisión.
Aquí está mi análisis de la imagen:
- País: Francia
- Región: Nueva Aquitania
- Ciudad: Hurón de Cabeza
Descripción del sujeto: A small, brightly painted boat floats calmly on the water, its red and black hull a striking contrast to the blue. The foreground is dotted with wooden posts sticking out of the water. The Arcachon lighthouse is visible behind the trees. The sandy beach stretches out in the distance.
Estimación de precisión: 85%s
