Search across models, guides, examples and the API.
↑↓ Navigateenter Openesc Close
Dashboard
live
MODEL IDalibaba-qwen2-5-vl-7b-instruct
Try in Playground

Qwen2.5-VL-7B-Instruct

Alibaba
by

Qwen2.5-VL-7B-Instruct is a multimodal model that processes images and text together to perform visual reasoning, captioning, question answering, and structured output generation. It integrates a vision encoder with a 7B instruction-tuned language backbone to support rich interactive multimodal understanding.

Qwen2.5-VL-7B-Instruct

caption

Wildfire Response Editorial Photo Caption$0.0032~9s
A firefighter in a yellow protective suit and red helmet stands amidst an orange grove, actively using a hose to combat a small but intense fire. The ground around the firefighter is scorched black, with visible embers and flames still burning. In the background, a fire truck with its lights on is parked, suggesting ongoing firefighting efforts. The setting appears to be a rural area with multiple orange trees, some of which have ripe fruit still hanging.
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@2',
  prompt: 'Write one accurate, detailed editorial caption describing only what is visibly present in this photograph. Identify the primary subject, clothing and equipment, observable action, setting, background activity, lighting, and signs of fire damage. Use clear newsroom prose and present tense. Do not guess the person\'s identity, exact location, date, agency, cause of the fire, or any facts that cannot be verified from the image.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/3d686d76-b572-4054-9b36-bfe91477888e.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@2",
            "prompt": "Write one accurate, detailed editorial caption describing only what is visibly present in this photograph. Identify the primary subject, clothing and equipment, observable action, setting, background activity, lighting, and signs of fire damage. Use clear newsroom prose and present tense. Do not guess the person's identity, exact location, date, agency, cause of the fire, or any facts that cannot be verified from the image.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/3d686d76-b572-4054-9b36-bfe91477888e.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": "0b76ae3b-de81-4872-a888-b9003807d77c",
      "model": "runware:152@2",
      "prompt": "Write one accurate, detailed editorial caption describing only what is visibly present in this photograph. Identify the primary subject, clothing and equipment, observable action, setting, background activity, lighting, and signs of fire damage. Use clear newsroom prose and present tense. Do not guess the person's identity, exact location, date, agency, cause of the fire, or any facts that cannot be verified from the image.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/3d686d76-b572-4054-9b36-bfe91477888e.jpg"
      }
    }
  ]'
runware run runware:152@2 \
  prompt="Write one accurate, detailed editorial caption describing only what is visibly present in this photograph. Identify the primary subject, clothing and equipment, observable action, setting, background activity, lighting, and signs of fire damage. Use clear newsroom prose and present tense. Do not guess the person's identity, exact location, date, agency, cause of the fire, or any facts that cannot be verified from the image." \
  inputs.image=https://assets.runware.ai/assets/inputs/3d686d76-b572-4054-9b36-bfe91477888e.jpg
{
  "taskType": "caption",
  "taskUUID": "0b76ae3b-de81-4872-a888-b9003807d77c",
  "model": "runware:152@2",
  "prompt": "Write one accurate, detailed editorial caption describing only what is visibly present in this photograph. Identify the primary subject, clothing and equipment, observable action, setting, background activity, lighting, and signs of fire damage. Use clear newsroom prose and present tense. Do not guess the person's identity, exact location, date, agency, cause of the fire, or any facts that cannot be verified from the image.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/3d686d76-b572-4054-9b36-bfe91477888e.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "0b76ae3b-de81-4872-a888-b9003807d77c",
  "text": "A firefighter in a yellow protective suit and red helmet stands amidst an orange grove, actively using a hose to combat a small but intense fire. The ground around the firefighter is scorched black, with visible embers and flames still burning. In the background, a fire truck with its lights on is parked, suggesting ongoing firefighting efforts. The setting appears to be a rural area with multiple orange trees, some of which have ripe fruit still hanging.",
  "cost": 0.0032
}

caption

Vehicle Damage Intake Caption$0.0019~7s
The image shows a white van parked on a wet asphalt surface near a sidewalk. The vehicle's front left side is significantly damaged, with noticeable dents and scratches on the fender and door. The headlight on the same side is intact but appears slightly misaligned. Debris, including small fragments of metal and plastic, is scattered on the ground around the van, suggesting recent impact. The windshield has a visible crack running across it.
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@2',
  prompt: 'Write an accurate, detailed insurance intake caption for this image. Identify the primary vehicle, camera viewpoint, visible damage, affected exterior components, debris, road and weather conditions, and relevant surroundings. Distinguish clearly between what is visibly damaged and what merely appears intact. Ground every statement only in observable image content; do not infer the cause of damage, mechanical condition, ownership, injuries, fault, location, or repair cost. Use one concise paragraph.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/3bd27eff-b313-4093-a524-39cc5eafab0b.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@2",
            "prompt": "Write an accurate, detailed insurance intake caption for this image. Identify the primary vehicle, camera viewpoint, visible damage, affected exterior components, debris, road and weather conditions, and relevant surroundings. Distinguish clearly between what is visibly damaged and what merely appears intact. Ground every statement only in observable image content; do not infer the cause of damage, mechanical condition, ownership, injuries, fault, location, or repair cost. Use one concise paragraph.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/3bd27eff-b313-4093-a524-39cc5eafab0b.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": "49df496f-52be-4470-a0a1-f5970bce80dd",
      "model": "runware:152@2",
      "prompt": "Write an accurate, detailed insurance intake caption for this image. Identify the primary vehicle, camera viewpoint, visible damage, affected exterior components, debris, road and weather conditions, and relevant surroundings. Distinguish clearly between what is visibly damaged and what merely appears intact. Ground every statement only in observable image content; do not infer the cause of damage, mechanical condition, ownership, injuries, fault, location, or repair cost. Use one concise paragraph.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/3bd27eff-b313-4093-a524-39cc5eafab0b.jpg"
      }
    }
  ]'
runware run runware:152@2 \
  prompt="Write an accurate, detailed insurance intake caption for this image. Identify the primary vehicle, camera viewpoint, visible damage, affected exterior components, debris, road and weather conditions, and relevant surroundings. Distinguish clearly between what is visibly damaged and what merely appears intact. Ground every statement only in observable image content; do not infer the cause of damage, mechanical condition, ownership, injuries, fault, location, or repair cost. Use one concise paragraph." \
  inputs.image=https://assets.runware.ai/assets/inputs/3bd27eff-b313-4093-a524-39cc5eafab0b.jpg
{
  "taskType": "caption",
  "taskUUID": "49df496f-52be-4470-a0a1-f5970bce80dd",
  "model": "runware:152@2",
  "prompt": "Write an accurate, detailed insurance intake caption for this image. Identify the primary vehicle, camera viewpoint, visible damage, affected exterior components, debris, road and weather conditions, and relevant surroundings. Distinguish clearly between what is visibly damaged and what merely appears intact. Ground every statement only in observable image content; do not infer the cause of damage, mechanical condition, ownership, injuries, fault, location, or repair cost. Use one concise paragraph.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/3bd27eff-b313-4093-a524-39cc5eafab0b.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "49df496f-52be-4470-a0a1-f5970bce80dd",
  "text": "The image shows a white van parked on a wet asphalt surface near a sidewalk. The vehicle's front left side is significantly damaged, with noticeable dents and scratches on the fender and door. The headlight on the same side is intact but appears slightly misaligned. Debris, including small fragments of metal and plastic, is scattered on the ground around the van, suggesting recent impact. The windshield has a visible crack running across it.",
  "cost": 0.0019
}

caption

Auction Furniture Lot Caption$0.0013~6s
The photograph showcases a vintage-style armchair positioned centrally within a softly-lit, minimalist room. The chair boasts a rich, dark wood frame exhibiting subtle distresss and a glossy, polished-like sheen indicative of polished or lacquered craftsmanship. Its curved-back and rounded-shaped legs contribute to a classic, slightly-form, while the woven-patterned cane detailing along the sides adds a touch of artisanal sophistication.
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@2',
  prompt: 'Write one accurate, detailed auction-catalog caption describing only what is visibly present in this photograph. Identify the primary furniture item, then describe its apparent form, colors, surface qualities, construction details, upholstery, viewpoint, visible wear or condition, placement, surrounding objects, lighting, and composition. Do not infer a designer, maker, date, provenance, authenticity, exact materials, dimensions, or historical style unless directly visible. Use precise, neutral language in a single paragraph of 90–130 words.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/0c273ba3-e0e3-439a-be77-1e6eb6586fcd.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@2",
            "prompt": "Write one accurate, detailed auction-catalog caption describing only what is visibly present in this photograph. Identify the primary furniture item, then describe its apparent form, colors, surface qualities, construction details, upholstery, viewpoint, visible wear or condition, placement, surrounding objects, lighting, and composition. Do not infer a designer, maker, date, provenance, authenticity, exact materials, dimensions, or historical style unless directly visible. Use precise, neutral language in a single paragraph of 90–130 words.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/0c273ba3-e0e3-439a-be77-1e6eb6586fcd.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": "3f81f9fe-4859-474b-856b-34f5e275adf5",
      "model": "runware:152@2",
      "prompt": "Write one accurate, detailed auction-catalog caption describing only what is visibly present in this photograph. Identify the primary furniture item, then describe its apparent form, colors, surface qualities, construction details, upholstery, viewpoint, visible wear or condition, placement, surrounding objects, lighting, and composition. Do not infer a designer, maker, date, provenance, authenticity, exact materials, dimensions, or historical style unless directly visible. Use precise, neutral language in a single paragraph of 90–130 words.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/0c273ba3-e0e3-439a-be77-1e6eb6586fcd.jpg"
      }
    }
  ]'
runware run runware:152@2 \
  prompt="Write one accurate, detailed auction-catalog caption describing only what is visibly present in this photograph. Identify the primary furniture item, then describe its apparent form, colors, surface qualities, construction details, upholstery, viewpoint, visible wear or condition, placement, surrounding objects, lighting, and composition. Do not infer a designer, maker, date, provenance, authenticity, exact materials, dimensions, or historical style unless directly visible. Use precise, neutral language in a single paragraph of 90–130 words." \
  inputs.image=https://assets.runware.ai/assets/inputs/0c273ba3-e0e3-439a-be77-1e6eb6586fcd.jpg
{
  "taskType": "caption",
  "taskUUID": "3f81f9fe-4859-474b-856b-34f5e275adf5",
  "model": "runware:152@2",
  "prompt": "Write one accurate, detailed auction-catalog caption describing only what is visibly present in this photograph. Identify the primary furniture item, then describe its apparent form, colors, surface qualities, construction details, upholstery, viewpoint, visible wear or condition, placement, surrounding objects, lighting, and composition. Do not infer a designer, maker, date, provenance, authenticity, exact materials, dimensions, or historical style unless directly visible. Use precise, neutral language in a single paragraph of 90–130 words.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/0c273ba3-e0e3-439a-be77-1e6eb6586fcd.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "3f81f9fe-4859-474b-856b-34f5e275adf5",
  "text": "The photograph showcases a vintage-style armchair positioned centrally within a softly-lit, minimalist room. The chair boasts a rich, dark wood frame exhibiting subtle distresss and a glossy, polished-like sheen indicative of polished or lacquered craftsmanship. Its curved-back and rounded-shaped legs contribute to a classic, slightly-form, while the woven-patterned cane detailing along the sides adds a touch of artisanal sophistication.",
  "cost": 0.0013
}

caption

Culinary Magazine Photo Caption$0.0013~6s
In a professional kitchen bathed in softlight, a chef meticulously craftsurs a lemon meringue tart atop a pristine white plate. With practiced hand, he wields a culinary torch, its blue flame dancinging gently across the toasted's crisp, craftinging a caramelized allure atop the creamy custard. The pastry, crowned with a plush, puffy cloud of toasted, restsands proudlyly amidst brass of gleaming copper potsers and a bowl of vibrant, sliced lemon.
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@2',
  prompt: 'Write an accurate, detailed editorial photo caption of 70–100 words. Describe the primary subject, the visible action, the dessert, relevant kitchen tools, surrounding activity, lighting, and composition. Ground every statement only in what can be directly observed in the image. Do not invent the chef\'s name, restaurant, location, recipe, occasion, emotions, or culinary technique beyond what is visibly evident. Use polished present-tense language suitable for a culinary magazine photo desk.',
  inputs: {
    image: 'https://assets.runware.ai/assets/inputs/b6720366-67fd-4ddf-9605-55b7c299bf7d.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@2",
            "prompt": "Write an accurate, detailed editorial photo caption of 70–100 words. Describe the primary subject, the visible action, the dessert, relevant kitchen tools, surrounding activity, lighting, and composition. Ground every statement only in what can be directly observed in the image. Do not invent the chef's name, restaurant, location, recipe, occasion, emotions, or culinary technique beyond what is visibly evident. Use polished present-tense language suitable for a culinary magazine photo desk.",
            "inputs": {
                "image": "https://assets.runware.ai/assets/inputs/b6720366-67fd-4ddf-9605-55b7c299bf7d.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": "85420125-6c48-4dd6-9f66-2fb7fefbc5b1",
      "model": "runware:152@2",
      "prompt": "Write an accurate, detailed editorial photo caption of 70–100 words. Describe the primary subject, the visible action, the dessert, relevant kitchen tools, surrounding activity, lighting, and composition. Ground every statement only in what can be directly observed in the image. Do not invent the chef's name, restaurant, location, recipe, occasion, emotions, or culinary technique beyond what is visibly evident. Use polished present-tense language suitable for a culinary magazine photo desk.",
      "inputs": {
        "image": "https://assets.runware.ai/assets/inputs/b6720366-67fd-4ddf-9605-55b7c299bf7d.jpg"
      }
    }
  ]'
runware run runware:152@2 \
  prompt="Write an accurate, detailed editorial photo caption of 70–100 words. Describe the primary subject, the visible action, the dessert, relevant kitchen tools, surrounding activity, lighting, and composition. Ground every statement only in what can be directly observed in the image. Do not invent the chef's name, restaurant, location, recipe, occasion, emotions, or culinary technique beyond what is visibly evident. Use polished present-tense language suitable for a culinary magazine photo desk." \
  inputs.image=https://assets.runware.ai/assets/inputs/b6720366-67fd-4ddf-9605-55b7c299bf7d.jpg
{
  "taskType": "caption",
  "taskUUID": "85420125-6c48-4dd6-9f66-2fb7fefbc5b1",
  "model": "runware:152@2",
  "prompt": "Write an accurate, detailed editorial photo caption of 70–100 words. Describe the primary subject, the visible action, the dessert, relevant kitchen tools, surrounding activity, lighting, and composition. Ground every statement only in what can be directly observed in the image. Do not invent the chef's name, restaurant, location, recipe, occasion, emotions, or culinary technique beyond what is visibly evident. Use polished present-tense language suitable for a culinary magazine photo desk.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/b6720366-67fd-4ddf-9605-55b7c299bf7d.jpg"
  }
}
Response
{
  "taskType": "imageCaption",
  "taskUUID": "85420125-6c48-4dd6-9f66-2fb7fefbc5b1",
  "text": "In a professional kitchen bathed in softlight, a chef meticulously craftsurs a lemon meringue tart atop a pristine white plate. With practiced hand, he wields a culinary torch, its blue flame dancinging gently across the toasted's crisp, craftinging a caramelized allure atop the creamy custard. The pastry, crowned with a plush, puffy cloud of toasted, restsands proudlyly amidst brass of gleaming copper potsers and a bowl of vibrant, sliced lemon.",
  "cost": 0.0013
}
Ask AI
Send feedback