↑↓ Navigateenter Openesc Close
Dashboard
MODEL IDalibaba-qwen2-5-vl-3b-instruct
live

Qwen2.5-VL-3B-Instruct

Alibaba
by Alibaba

Qwen2.5-VL-3B-Instruct is a multimodal model that processes images and text together to perform visual reasoning, captioning, question answering, and structured output tasks. It integrates a vision encoder with an instruction-tuned language backbone to support complex visual understanding and interactive multimodal responses.

Qwen2.5-VL-3B-Instruct
caption

Fashion Editorial Accessibility Caption

In a well-lit, professional makeup station, a model stands poised in a striking blue, ruffled gown as makeup artists meticulously apply finishing touches. The model's vibrant red hair contrasts sharply with her elegant attire. To the right, a rack holds various dresses, including a flowing white gown and a patterned dress, suggesting a diverse wardrobe selection. The floor is marked with white lines, likely indicating designated areas for different tasks.
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'runware:152@1',
  prompt: 'Write one accurate, detailed accessibility caption for this fashion editorial image. Ground every statement only in clearly visible content. Identify the main subjects, clothing, actions, left-to-right positions, foreground and background relationships, lighting, colors, and notable environmental details. Do not identify people, brands, designers, locations, emotions, or event names unless visibly confirmed. Do not speculate about intent or circumstances. Use clear present-tense prose in 90–130 words.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/94b27859-ec9d-480c-9adf-a6356e3f85ec.jpg'
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "runware:152@1",
            "prompt": "Write one accurate, detailed accessibility caption for this fashion editorial image. Ground every statement only in clearly visible content. Identify the main subjects, clothing, actions, left-to-right positions, foreground and background relationships, lighting, colors, and notable environmental details. Do not identify people, brands, designers, locations, emotions, or event names unless visibly confirmed. Do not speculate about intent or circumstances. Use clear present-tense prose in 90–130 words.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/94b27859-ec9d-480c-9adf-a6356e3f85ec.jpg"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "caption",
      "taskUUID": "1c678388-2490-40dd-ab90-794e439df9cf",
      "model": "runware:152@1",
      "prompt": "Write one accurate, detailed accessibility caption for this fashion editorial image. Ground every statement only in clearly visible content. Identify the main subjects, clothing, actions, left-to-right positions, foreground and background relationships, lighting, colors, and notable environmental details. Do not identify people, brands, designers, locations, emotions, or event names unless visibly confirmed. Do not speculate about intent or circumstances. Use clear present-tense prose in 90–130 words.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/94b27859-ec9d-480c-9adf-a6356e3f85ec.jpg"
      }
    }
  ]'
runware run runware:152@1 \
  prompt="Write one accurate, detailed accessibility caption for this fashion editorial image. Ground every statement only in clearly visible content. Identify the main subjects, clothing, actions, left-to-right positions, foreground and background relationships, lighting, colors, and notable environmental details. Do not identify people, brands, designers, locations, emotions, or event names unless visibly confirmed. Do not speculate about intent or circumstances. Use clear present-tense prose in 90–130 words." \
  inputs.image=https://assets.runware.ai/assets/inputs/94b27859-ec9d-480c-9adf-a6356e3f85ec.jpg
{
  "taskType": "caption",
  "taskUUID": "1c678388-2490-40dd-ab90-794e439df9cf",
  "model": "runware:152@1",
  "prompt": "Write one accurate, detailed accessibility caption for this fashion editorial image. Ground every statement only in clearly visible content. Identify the main subjects, clothing, actions, left-to-right positions, foreground and background relationships, lighting, colors, and notable environmental details. Do not identify people, brands, designers, locations, emotions, or event names unless visibly confirmed. Do not speculate about intent or circumstances. Use clear present-tense prose in 90–130 words.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/94b27859-ec9d-480c-9adf-a6356e3f85ec.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "1c678388-2490-40dd-ab90-794e439df9cf",
  "text": "In a well-lit, professional makeup station, a model stands poised in a striking blue, ruffled gown as makeup artists meticulously apply finishing touches. The model's vibrant red hair contrasts sharply with her elegant attire. To the right, a rack holds various dresses, including a flowing white gown and a patterned dress, suggesting a diverse wardrobe selection. The floor is marked with white lines, likely indicating designated areas for different tasks.",
  "cost": 0.0019
}
caption

Marine Conservation Field Report Caption

A group of marine conservationists is conducting nighttime research on a green sea turtle on a sandy beach. The turtle is illuminated by red lights, likely for identification purposes. One researcher holds a clipboard, while another uses a device, possibly a GPS tracker, attached to the turtle's shell. The team is equipped with various tools and equipment, including a case containing batteries and other devices. The beach appears calm with minimal footprints, suggesting low human activity.
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'runware:152@1',
  prompt: 'Write an accurate, detailed caption for a professional marine conservation field report. Describe only what is visibly supported by the image, including the main subjects, their actions, the equipment in use, relative positions, beach conditions, lighting, tracks, shoreline, and relevant background activity. Do not invent names, location, date, organization, turtle species, research purpose, measurements, or outcomes. If a detail is uncertain, use cautious visual language rather than guessing. Produce one polished paragraph of 90–130 words in a neutral documentary tone.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/7fa3243b-ca28-4a35-816b-466e460e2014.jpg'
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "runware:152@1",
            "prompt": "Write an accurate, detailed caption for a professional marine conservation field report. Describe only what is visibly supported by the image, including the main subjects, their actions, the equipment in use, relative positions, beach conditions, lighting, tracks, shoreline, and relevant background activity. Do not invent names, location, date, organization, turtle species, research purpose, measurements, or outcomes. If a detail is uncertain, use cautious visual language rather than guessing. Produce one polished paragraph of 90–130 words in a neutral documentary tone.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/7fa3243b-ca28-4a35-816b-466e460e2014.jpg"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "caption",
      "taskUUID": "23d0a3f1-71e2-4368-b936-97e8fda943b5",
      "model": "runware:152@1",
      "prompt": "Write an accurate, detailed caption for a professional marine conservation field report. Describe only what is visibly supported by the image, including the main subjects, their actions, the equipment in use, relative positions, beach conditions, lighting, tracks, shoreline, and relevant background activity. Do not invent names, location, date, organization, turtle species, research purpose, measurements, or outcomes. If a detail is uncertain, use cautious visual language rather than guessing. Produce one polished paragraph of 90–130 words in a neutral documentary tone.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/7fa3243b-ca28-4a35-816b-466e460e2014.jpg"
      }
    }
  ]'
runware run runware:152@1 \
  prompt="Write an accurate, detailed caption for a professional marine conservation field report. Describe only what is visibly supported by the image, including the main subjects, their actions, the equipment in use, relative positions, beach conditions, lighting, tracks, shoreline, and relevant background activity. Do not invent names, location, date, organization, turtle species, research purpose, measurements, or outcomes. If a detail is uncertain, use cautious visual language rather than guessing. Produce one polished paragraph of 90–130 words in a neutral documentary tone." \
  inputs.image=https://assets.runware.ai/assets/inputs/7fa3243b-ca28-4a35-816b-466e460e2014.jpg
{
  "taskType": "caption",
  "taskUUID": "23d0a3f1-71e2-4368-b936-97e8fda943b5",
  "model": "runware:152@1",
  "prompt": "Write an accurate, detailed caption for a professional marine conservation field report. Describe only what is visibly supported by the image, including the main subjects, their actions, the equipment in use, relative positions, beach conditions, lighting, tracks, shoreline, and relevant background activity. Do not invent names, location, date, organization, turtle species, research purpose, measurements, or outcomes. If a detail is uncertain, use cautious visual language rather than guessing. Produce one polished paragraph of 90–130 words in a neutral documentary tone.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/7fa3243b-ca28-4a35-816b-466e460e2014.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "23d0a3f1-71e2-4368-b936-97e8fda943b5",
  "text": "A group of marine conservationists is conducting nighttime research on a green sea turtle on a sandy beach. The turtle is illuminated by red lights, likely for identification purposes. One researcher holds a clipboard, while another uses a device, possibly a GPS tracker, attached to the turtle's shell. The team is equipped with various tools and equipment, including a case containing batteries and other devices. The beach appears calm with minimal footprints, suggesting low human activity.",
  "cost": 0.0013
}
caption

Urban Flood Response Caption

In a rainy urban setting, emergency responders clad in bright orange uniforms are seen assisting a person seated in a small inflatable boat. The boat is being maneuvered by two individuals, one of whom is holding onto a rope connected to the boat. Nearby, a cart filled with stacks of bottled water is positioned on the wet pavement, indicating a possible evacuation or relief effort. In the background, a bus is partially submerged in floodwaters, emphasizing the severity of the situation.
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'runware:152@1',
  prompt: 'Write one accurate, detailed, publication-ready caption for this documentary image. Describe the principal subjects, their visible actions, relevant clothing or equipment, clear spatial relationships from foreground to background, and important environmental details. Ground every statement only in what can be directly seen. Do not invent names, dates, locations, organizations, causes, outcomes, dialogue, emotions, or personal relationships. Do not infer identities or circumstances beyond visible evidence. Mention written text only when it is clearly legible. Use neutral journalistic language in a single coherent paragraph.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/c854e667-6c26-47f0-a6e5-106728cb2d4d.jpg'
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "runware:152@1",
            "prompt": "Write one accurate, detailed, publication-ready caption for this documentary image. Describe the principal subjects, their visible actions, relevant clothing or equipment, clear spatial relationships from foreground to background, and important environmental details. Ground every statement only in what can be directly seen. Do not invent names, dates, locations, organizations, causes, outcomes, dialogue, emotions, or personal relationships. Do not infer identities or circumstances beyond visible evidence. Mention written text only when it is clearly legible. Use neutral journalistic language in a single coherent paragraph.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/c854e667-6c26-47f0-a6e5-106728cb2d4d.jpg"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "caption",
      "taskUUID": "899251f4-adc9-4070-a387-3b00e5d4e890",
      "model": "runware:152@1",
      "prompt": "Write one accurate, detailed, publication-ready caption for this documentary image. Describe the principal subjects, their visible actions, relevant clothing or equipment, clear spatial relationships from foreground to background, and important environmental details. Ground every statement only in what can be directly seen. Do not invent names, dates, locations, organizations, causes, outcomes, dialogue, emotions, or personal relationships. Do not infer identities or circumstances beyond visible evidence. Mention written text only when it is clearly legible. Use neutral journalistic language in a single coherent paragraph.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/c854e667-6c26-47f0-a6e5-106728cb2d4d.jpg"
      }
    }
  ]'
runware run runware:152@1 \
  prompt="Write one accurate, detailed, publication-ready caption for this documentary image. Describe the principal subjects, their visible actions, relevant clothing or equipment, clear spatial relationships from foreground to background, and important environmental details. Ground every statement only in what can be directly seen. Do not invent names, dates, locations, organizations, causes, outcomes, dialogue, emotions, or personal relationships. Do not infer identities or circumstances beyond visible evidence. Mention written text only when it is clearly legible. Use neutral journalistic language in a single coherent paragraph." \
  inputs.image=https://assets.runware.ai/assets/inputs/c854e667-6c26-47f0-a6e5-106728cb2d4d.jpg
{
  "taskType": "caption",
  "taskUUID": "899251f4-adc9-4070-a387-3b00e5d4e890",
  "model": "runware:152@1",
  "prompt": "Write one accurate, detailed, publication-ready caption for this documentary image. Describe the principal subjects, their visible actions, relevant clothing or equipment, clear spatial relationships from foreground to background, and important environmental details. Ground every statement only in what can be directly seen. Do not invent names, dates, locations, organizations, causes, outcomes, dialogue, emotions, or personal relationships. Do not infer identities or circumstances beyond visible evidence. Mention written text only when it is clearly legible. Use neutral journalistic language in a single coherent paragraph.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/c854e667-6c26-47f0-a6e5-106728cb2d4d.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "899251f4-adc9-4070-a387-3b00e5d4e890",
  "text": "In a rainy urban setting, emergency responders clad in bright orange uniforms are seen assisting a person seated in a small inflatable boat. The boat is being maneuvered by two individuals, one of whom is holding onto a rope connected to the boat. Nearby, a cart filled with stacks of bottled water is positioned on the wet pavement, indicating a possible evacuation or relief effort. In the background, a bus is partially submerged in floodwaters, emphasizing the severity of the situation.",
  "cost": 0.0032
}
caption

Construction Safety Audit Caption

A group of construction workers is gathered under a bridge, engaged in various tasks related to a construction project. They are wearing high-visibility vests and hard hats, indicating adherence to safety protocols. One worker is operating a laser level, which is placed on a tripod, suggesting they are measuring or leveling surfaces. Another worker is holding a rolled-up blueprint, likely reviewing plans or discussing the project's progress. Nearby, there is a crane with its arm extended, possibly lifting materials or equipment.
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'runware:152@1',
  prompt: 'Write one accurate, detailed caption for this construction-site photograph. Ground every statement only in visible evidence. Describe the people, their observable actions, clothing and safety equipment, machinery, tools, materials, spatial relationships, site conditions, background, and lighting. Include reliable counts and legible text or markings when visible. Do not infer identities, job titles, project status, hazards, causes, intentions, or events outside the frame. If a detail is unclear, describe it cautiously rather than guessing. Return only the caption.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/0cd6b11b-1fd1-4656-806b-d429fd6a7b95.jpg'
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "runware:152@1",
            "prompt": "Write one accurate, detailed caption for this construction-site photograph. Ground every statement only in visible evidence. Describe the people, their observable actions, clothing and safety equipment, machinery, tools, materials, spatial relationships, site conditions, background, and lighting. Include reliable counts and legible text or markings when visible. Do not infer identities, job titles, project status, hazards, causes, intentions, or events outside the frame. If a detail is unclear, describe it cautiously rather than guessing. Return only the caption.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/0cd6b11b-1fd1-4656-806b-d429fd6a7b95.jpg"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "caption",
      "taskUUID": "b8254982-22f6-452d-a72d-212afe27e5c0",
      "model": "runware:152@1",
      "prompt": "Write one accurate, detailed caption for this construction-site photograph. Ground every statement only in visible evidence. Describe the people, their observable actions, clothing and safety equipment, machinery, tools, materials, spatial relationships, site conditions, background, and lighting. Include reliable counts and legible text or markings when visible. Do not infer identities, job titles, project status, hazards, causes, intentions, or events outside the frame. If a detail is unclear, describe it cautiously rather than guessing. Return only the caption.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/0cd6b11b-1fd1-4656-806b-d429fd6a7b95.jpg"
      }
    }
  ]'
runware run runware:152@1 \
  prompt="Write one accurate, detailed caption for this construction-site photograph. Ground every statement only in visible evidence. Describe the people, their observable actions, clothing and safety equipment, machinery, tools, materials, spatial relationships, site conditions, background, and lighting. Include reliable counts and legible text or markings when visible. Do not infer identities, job titles, project status, hazards, causes, intentions, or events outside the frame. If a detail is unclear, describe it cautiously rather than guessing. Return only the caption." \
  inputs.image=https://assets.runware.ai/assets/inputs/0cd6b11b-1fd1-4656-806b-d429fd6a7b95.jpg
{
  "taskType": "caption",
  "taskUUID": "b8254982-22f6-452d-a72d-212afe27e5c0",
  "model": "runware:152@1",
  "prompt": "Write one accurate, detailed caption for this construction-site photograph. Ground every statement only in visible evidence. Describe the people, their observable actions, clothing and safety equipment, machinery, tools, materials, spatial relationships, site conditions, background, and lighting. Include reliable counts and legible text or markings when visible. Do not infer identities, job titles, project status, hazards, causes, intentions, or events outside the frame. If a detail is unclear, describe it cautiously rather than guessing. Return only the caption.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/0cd6b11b-1fd1-4656-806b-d429fd6a7b95.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "b8254982-22f6-452d-a72d-212afe27e5c0",
  "text": "A group of construction workers is gathered under a bridge, engaged in various tasks related to a construction project. They are wearing high-visibility vests and hard hats, indicating adherence to safety protocols. One worker is operating a laser level, which is placed on a tripod, suggesting they are measuring or leveling surfaces. Another worker is holding a rolled-up blueprint, likely reviewing plans or discussing the project's progress. Nearby, there is a crane with its arm extended, possibly lifting materials or equipment.",
  "cost": 0.0032
}
Caption

Salt-Flat Breakfast Balloonists

Two individuals are enjoying a picnic on a vast, snowy plain under a clear sky. They are seated on patterned rugs, surrounded by a colorful hot air balloon festival. The balloons are vibrant, with hues of red, yellow, blue, and green, floating above them. The setting sun casts a warm glow over the scene, creating a serene and picturesque atmosphere.
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'runware:152@1',
  prompt: 'Write a vivid, accurate caption for this image in 2-3 sentences. Describe the main subjects, setting, notable objects, colors, lighting, and the overall mood. Avoid speculation beyond what is clearly visible.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/02da3f55-7a4b-4064-a905-ca325e849a70.jpg'
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "runware:152@1",
            "prompt": "Write a vivid, accurate caption for this image in 2-3 sentences. Describe the main subjects, setting, notable objects, colors, lighting, and the overall mood. Avoid speculation beyond what is clearly visible.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/02da3f55-7a4b-4064-a905-ca325e849a70.jpg"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "caption",
      "taskUUID": "e340cc77-2772-4f13-8297-1a7dffcf525c",
      "model": "runware:152@1",
      "prompt": "Write a vivid, accurate caption for this image in 2-3 sentences. Describe the main subjects, setting, notable objects, colors, lighting, and the overall mood. Avoid speculation beyond what is clearly visible.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/02da3f55-7a4b-4064-a905-ca325e849a70.jpg"
      }
    }
  ]'
runware run runware:152@1 \
  prompt="Write a vivid, accurate caption for this image in 2-3 sentences. Describe the main subjects, setting, notable objects, colors, lighting, and the overall mood. Avoid speculation beyond what is clearly visible." \
  inputs.image=https://assets.runware.ai/assets/inputs/02da3f55-7a4b-4064-a905-ca325e849a70.jpg
{
  "taskType": "caption",
  "taskUUID": "e340cc77-2772-4f13-8297-1a7dffcf525c",
  "model": "runware:152@1",
  "prompt": "Write a vivid, accurate caption for this image in 2-3 sentences. Describe the main subjects, setting, notable objects, colors, lighting, and the overall mood. Avoid speculation beyond what is clearly visible.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/02da3f55-7a4b-4064-a905-ca325e849a70.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "e340cc77-2772-4f13-8297-1a7dffcf525c",
  "text": "Two individuals are enjoying a picnic on a vast, snowy plain under a clear sky. They are seated on patterned rugs, surrounded by a colorful hot air balloon festival. The balloons are vibrant, with hues of red, yellow, blue, and green, floating above them. The setting sun casts a warm glow over the scene, creating a serene and picturesque atmosphere.",
  "cost": 0.0019
}
Caption

Rooftop Pigeon Racing Finale

A lively rooftop gathering features two men flying colorful kites amidst a flock of pigeons, with a backdrop of traditional buildings and a minaret silhouetted against the setting sun.
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'runware:152@1',
  prompt: 'Write a concise, vivid caption in 1-2 sentences describing the main action, setting, and mood of this image.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/7590c546-9819-4c3b-b3a7-3b16838e1222.jpg'
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "runware:152@1",
            "prompt": "Write a concise, vivid caption in 1-2 sentences describing the main action, setting, and mood of this image.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/7590c546-9819-4c3b-b3a7-3b16838e1222.jpg"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "caption",
      "taskUUID": "66a9623a-dbd9-4db9-8975-592584b3d844",
      "model": "runware:152@1",
      "prompt": "Write a concise, vivid caption in 1-2 sentences describing the main action, setting, and mood of this image.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/7590c546-9819-4c3b-b3a7-3b16838e1222.jpg"
      }
    }
  ]'
runware run runware:152@1 \
  prompt="Write a concise, vivid caption in 1-2 sentences describing the main action, setting, and mood of this image." \
  inputs.image=https://assets.runware.ai/assets/inputs/7590c546-9819-4c3b-b3a7-3b16838e1222.jpg
{
  "taskType": "caption",
  "taskUUID": "66a9623a-dbd9-4db9-8975-592584b3d844",
  "model": "runware:152@1",
  "prompt": "Write a concise, vivid caption in 1-2 sentences describing the main action, setting, and mood of this image.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/7590c546-9819-4c3b-b3a7-3b16838e1222.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "66a9623a-dbd9-4db9-8975-592584b3d844",
  "text": "A lively rooftop gathering features two men flying colorful kites amidst a flock of pigeons, with a backdrop of traditional buildings and a minaret silhouetted against the setting sun.",
  "cost": 0.0013
}
Caption

Harbor Market Eclipse Tableau

In this vibrant seaside town, a dramatic solar eclipse casts a radiant halo over the bustling market, where vendors sell fresh produce and seafood. Children play near a makeshift telescope, while adults tend to their stalls under the enchanting sky. The town's architecture features colorful awnings and signs in Arabic script, adding to the lively atmosphere. A large ship sails past the dock, and seagulls soar above, enhancing the scene's dynamic energy.
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'runware:152@1',
  prompt: 'Write a precise, vivid caption for this image in 2-3 sentences. Identify the main setting, the unusual sky event, notable human activity, and at least five specific visual details without guessing hidden context.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/13dcd4da-6c25-4422-b900-b3abab18ce24.jpg'
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "runware:152@1",
            "prompt": "Write a precise, vivid caption for this image in 2-3 sentences. Identify the main setting, the unusual sky event, notable human activity, and at least five specific visual details without guessing hidden context.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/13dcd4da-6c25-4422-b900-b3abab18ce24.jpg"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "caption",
      "taskUUID": "3e62120b-9210-4117-9231-9f6bdbfecc8a",
      "model": "runware:152@1",
      "prompt": "Write a precise, vivid caption for this image in 2-3 sentences. Identify the main setting, the unusual sky event, notable human activity, and at least five specific visual details without guessing hidden context.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/13dcd4da-6c25-4422-b900-b3abab18ce24.jpg"
      }
    }
  ]'
runware run runware:152@1 \
  prompt="Write a precise, vivid caption for this image in 2-3 sentences. Identify the main setting, the unusual sky event, notable human activity, and at least five specific visual details without guessing hidden context." \
  inputs.image=https://assets.runware.ai/assets/inputs/13dcd4da-6c25-4422-b900-b3abab18ce24.jpg
{
  "taskType": "caption",
  "taskUUID": "3e62120b-9210-4117-9231-9f6bdbfecc8a",
  "model": "runware:152@1",
  "prompt": "Write a precise, vivid caption for this image in 2-3 sentences. Identify the main setting, the unusual sky event, notable human activity, and at least five specific visual details without guessing hidden context.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/13dcd4da-6c25-4422-b900-b3abab18ce24.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "3e62120b-9210-4117-9231-9f6bdbfecc8a",
  "text": "In this vibrant seaside town, a dramatic solar eclipse casts a radiant halo over the bustling market, where vendors sell fresh produce and seafood. Children play near a makeshift telescope, while adults tend to their stalls under the enchanting sky. The town's architecture features colorful awnings and signs in Arabic script, adding to the lively atmosphere. A large ship sails past the dock, and seagulls soar above, enhancing the scene's dynamic energy.",
  "cost": 0.0026
}
Caption

Taxidermy Workshop Curiosity Cabinet

In a dimly lit, sepia-toned laboratory filled with shelves of jars containing various specimens, two birds stand on a wooden desk. The desk is cluttered with tools, including a magnifying glass, a small knife, and a green and red object that resembles a toy car. A large glass dome encases a collection of feathers and other natural items. To the left, a book lies open, while to the right, a skull and other anatomical models are displayed.
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'runware:152@1',
  prompt: 'Write a precise 5-7 sentence caption describing the scene, highlighting the main subject, notable objects, materials, lighting, and overall atmosphere. Mention spatial relationships clearly and avoid speculation beyond what is visible.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/465571c4-411b-476e-a975-6e8cc06c397d.jpg'
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "runware:152@1",
            "prompt": "Write a precise 5-7 sentence caption describing the scene, highlighting the main subject, notable objects, materials, lighting, and overall atmosphere. Mention spatial relationships clearly and avoid speculation beyond what is visible.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/465571c4-411b-476e-a975-6e8cc06c397d.jpg"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "caption",
      "taskUUID": "74c7c126-bc3d-4e55-b8fa-36e20e2a4e62",
      "model": "runware:152@1",
      "prompt": "Write a precise 5-7 sentence caption describing the scene, highlighting the main subject, notable objects, materials, lighting, and overall atmosphere. Mention spatial relationships clearly and avoid speculation beyond what is visible.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/465571c4-411b-476e-a975-6e8cc06c397d.jpg"
      }
    }
  ]'
runware run runware:152@1 \
  prompt="Write a precise 5-7 sentence caption describing the scene, highlighting the main subject, notable objects, materials, lighting, and overall atmosphere. Mention spatial relationships clearly and avoid speculation beyond what is visible." \
  inputs.image=https://assets.runware.ai/assets/inputs/465571c4-411b-476e-a975-6e8cc06c397d.jpg
{
  "taskType": "caption",
  "taskUUID": "74c7c126-bc3d-4e55-b8fa-36e20e2a4e62",
  "model": "runware:152@1",
  "prompt": "Write a precise 5-7 sentence caption describing the scene, highlighting the main subject, notable objects, materials, lighting, and overall atmosphere. Mention spatial relationships clearly and avoid speculation beyond what is visible.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/465571c4-411b-476e-a975-6e8cc06c397d.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "74c7c126-bc3d-4e55-b8fa-36e20e2a4e62",
  "text": "In a dimly lit, sepia-toned laboratory filled with shelves of jars containing various specimens, two birds stand on a wooden desk. The desk is cluttered with tools, including a magnifying glass, a small knife, and a green and red object that resembles a toy car. A large glass dome encases a collection of feathers and other natural items. To the left, a book lies open, while to the right, a skull and other anatomical models are displayed.",
  "cost": 0.0026
}
Ask AI
Send feedback