Search across models, guides, examples and the API.
↑↓ Navigateenter Openesc Close
Dashboard
live
MODEL IDalibaba-qwen2-5-vl-3b-instruct
Try in Playground

Qwen2.5-VL-3B-Instruct

Alibaba
by

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

Construction Safety Audit Caption$0.0032~16s
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.
Try in Playground
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

Marine Conservation Field Report Caption$0.0013~5s
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.
Try in Playground
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$0.0032~14s
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.
Try in Playground
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

Fashion Editorial Accessibility Caption$0.0019~7s
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.
Try in Playground
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
}
Ask AI
Send feedback