Prediction

lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575

Model

lucataco/apollo-7b:e282f76d

ID

bw7z78n9e9rme0ckt5aszgcf9g

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

85.7s

Created

5 months ago

Input

top_p: 0.7
video
prompt: Describe this video in detail
temperature: 0.4
max_new_tokens: 256

{
  "top_p": 0.7,
  "video": "https://replicate.delivery/pbxt/M9kGHuJMeAKZs0eSbaEk6hCc7zqY4Tg94IxWwDpC5hRiuBPY/astro.mp4",
  "prompt": "Describe this video in detail",
  "temperature": 0.4,
  "max_new_tokens": 256
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run lucataco/apollo-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575",
  {
    input: {
      top_p: 0.7,
      video: "https://replicate.delivery/pbxt/M9kGHuJMeAKZs0eSbaEk6hCc7zqY4Tg94IxWwDpC5hRiuBPY/astro.mp4",
      prompt: "Describe this video in detail",
      temperature: 0.4,
      max_new_tokens: 256
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run lucataco/apollo-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575",
    input={
        "top_p": 0.7,
        "video": "https://replicate.delivery/pbxt/M9kGHuJMeAKZs0eSbaEk6hCc7zqY4Tg94IxWwDpC5hRiuBPY/astro.mp4",
        "prompt": "Describe this video in detail",
        "temperature": 0.4,
        "max_new_tokens": 256
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run lucataco/apollo-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575",
    "input": {
      "top_p": 0.7,
      "video": "https://replicate.delivery/pbxt/M9kGHuJMeAKZs0eSbaEk6hCc7zqY4Tg94IxWwDpC5hRiuBPY/astro.mp4",
      "prompt": "Describe this video in detail",
      "temperature": 0.4,
      "max_new_tokens": 256
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

The video features an astronaut in a white spacesuit walking on the moon's surface. The background showcases a large, detailed moon against a starry sky. As the astronaut walks, they begin to run and eventually leap into the air, floating above the moon's rocky terrain. The scene transitions to the astronaut drifting away from the moon, with the lunar landscape and the moon itself visible in the background. The video concludes with the astronaut continuing to float in space, gazing at the moon.

{
  "completed_at": "2024-12-16T21:19:18.081679Z",
  "created_at": "2024-12-16T21:17:52.370000Z",
  "data_removed": false,
  "error": null,
  "id": "bw7z78n9e9rme0ckt5aszgcf9g",
  "input": {
    "top_p": 0.7,
    "video": "https://replicate.delivery/pbxt/M9kGHuJMeAKZs0eSbaEk6hCc7zqY4Tg94IxWwDpC5hRiuBPY/astro.mp4",
    "prompt": "Describe this video in detail",
    "temperature": 0.4,
    "max_new_tokens": 256
  },
  "logs": "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.\nwarnings.warn(\n/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/utils/checkpoint.py:61: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\nwarnings.warn(\nThe attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.",
  "metrics": {
    "predict_time": 3.133147223,
    "total_time": 85.711679
  },
  "output": "The video features an astronaut in a white spacesuit walking on the moon's surface. The background showcases a large, detailed moon against a starry sky. As the astronaut walks, they begin to run and eventually leap into the air, floating above the moon's rocky terrain. The scene transitions to the astronaut drifting away from the moon, with the lunar landscape and the moon itself visible in the background. The video concludes with the astronaut continuing to float in space, gazing at the moon.",
  "started_at": "2024-12-16T21:19:14.948532Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/bw7z78n9e9rme0ckt5aszgcf9g",
    "cancel": "https://api.replicate.com/v1/predictions/bw7z78n9e9rme0ckt5aszgcf9g/cancel"
  },
  "version": "e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575"
}

Generated in

3.1 seconds

Tweak it Share Report

Prediction

lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575

Model

lucataco/apollo-7b:e282f76d

ID

ja31pgh1txrm80ckt5crt8r5n4

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

69.7s

Created

5 months ago

Input

top_p: 0.7
video
prompt: Describe this video in detail
temperature: 0.4
max_new_tokens: 256

{
  "top_p": 0.7,
  "video": "https://replicate.delivery/pbxt/M9kJs6YC2anfvw6JIoRWFCFWUuLkHcr0oXvVso5SYiEMw41e/office.mp4",
  "prompt": "Describe this video in detail",
  "temperature": 0.4,
  "max_new_tokens": 256
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run lucataco/apollo-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575",
  {
    input: {
      top_p: 0.7,
      video: "https://replicate.delivery/pbxt/M9kJs6YC2anfvw6JIoRWFCFWUuLkHcr0oXvVso5SYiEMw41e/office.mp4",
      prompt: "Describe this video in detail",
      temperature: 0.4,
      max_new_tokens: 256
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run lucataco/apollo-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575",
    input={
        "top_p": 0.7,
        "video": "https://replicate.delivery/pbxt/M9kJs6YC2anfvw6JIoRWFCFWUuLkHcr0oXvVso5SYiEMw41e/office.mp4",
        "prompt": "Describe this video in detail",
        "temperature": 0.4,
        "max_new_tokens": 256
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run lucataco/apollo-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575",
    "input": {
      "top_p": 0.7,
      "video": "https://replicate.delivery/pbxt/M9kJs6YC2anfvw6JIoRWFCFWUuLkHcr0oXvVso5SYiEMw41e/office.mp4",
      "prompt": "Describe this video in detail",
      "temperature": 0.4,
      "max_new_tokens": 256
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

The video begins with a professional meeting between two individuals seated at a wooden desk. The person on the left, dressed in a white shirt and glasses, is holding a pen and appears to be speaking or listening attentively. The person on the right, wearing a white blouse, has a laptop open in front of them and is also engaged in the conversation. The background features a modern, geometric wall design with alternating light and dark panels. On the desk, there are various items including a black pen holder, a white tumbler, some papers, and a pair of glasses. The person on the right gestures with their hand while talking, indicating an active discussion. The scene develops as the person on the right extends their arm outward, pointing towards something off-screen, suggesting they are making a specific reference or directing attention to another individual or object not visible in the frame. The video continues with the same setting, where the person on the right remains actively engaged in the conversation, gesturing with their hand and extending their arm outward, pointing towards something off-screen. The desk still holds the same items, and the background maintains the modern, geometric wall design. The video wraps up with the person on the right continuing to gesture, indicating an ongoing and dynamic discussion.

{
  "completed_at": "2024-12-16T21:22:49.538537Z",
  "created_at": "2024-12-16T21:21:39.799000Z",
  "data_removed": false,
  "error": null,
  "id": "ja31pgh1txrm80ckt5crt8r5n4",
  "input": {
    "top_p": 0.7,
    "video": "https://replicate.delivery/pbxt/M9kJs6YC2anfvw6JIoRWFCFWUuLkHcr0oXvVso5SYiEMw41e/office.mp4",
    "prompt": "Describe this video in detail",
    "temperature": 0.4,
    "max_new_tokens": 256
  },
  "logs": "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.\nwarnings.warn(\n/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/utils/checkpoint.py:61: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\nwarnings.warn(\nThe attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.",
  "metrics": {
    "predict_time": 8.26675931,
    "total_time": 69.739537
  },
  "output": "The video begins with a professional meeting between two individuals seated at a wooden desk. The person on the left, dressed in a white shirt and glasses, is holding a pen and appears to be speaking or listening attentively. The person on the right, wearing a white blouse, has a laptop open in front of them and is also engaged in the conversation. The background features a modern, geometric wall design with alternating light and dark panels. On the desk, there are various items including a black pen holder, a white tumbler, some papers, and a pair of glasses. The person on the right gestures with their hand while talking, indicating an active discussion. The scene develops as the person on the right extends their arm outward, pointing towards something off-screen, suggesting they are making a specific reference or directing attention to another individual or object not visible in the frame. The video continues with the same setting, where the person on the right remains actively engaged in the conversation, gesturing with their hand and extending their arm outward, pointing towards something off-screen. The desk still holds the same items, and the background maintains the modern, geometric wall design. The video wraps up with the person on the right continuing to gesture, indicating an ongoing and dynamic discussion.",
  "started_at": "2024-12-16T21:22:41.271778Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ja31pgh1txrm80ckt5crt8r5n4",
    "cancel": "https://api.replicate.com/v1/predictions/ja31pgh1txrm80ckt5crt8r5n4/cancel"
  },
  "version": "e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575"
}

Generated in

8.3 seconds

Tweak it Share Report

Prediction

lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575

Model

lucataco/apollo-7b:e282f76d

ID

yqynbynbxsrma0ckt7h8wwn2hc

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

2m

Created

5 months ago by @lucataco

Input

top_p: 0.7
video
prompt: What watch brands appear in the video?
temperature: 0.4
max_new_tokens: 256

{
  "top_p": 0.7,
  "video": "https://replicate.delivery/pbxt/M9mbrDJ7QIDkWZLSkIYjfoe1xxsr4cfngJq477mfJjv5UcFI/example2.mp4",
  "prompt": "What watch brands appear in the video?",
  "temperature": 0.4,
  "max_new_tokens": 256
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run lucataco/apollo-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575",
  {
    input: {
      top_p: 0.7,
      video: "https://replicate.delivery/pbxt/M9mbrDJ7QIDkWZLSkIYjfoe1xxsr4cfngJq477mfJjv5UcFI/example2.mp4",
      prompt: "What watch brands appear in the video?",
      temperature: 0.4,
      max_new_tokens: 256
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run lucataco/apollo-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575",
    input={
        "top_p": 0.7,
        "video": "https://replicate.delivery/pbxt/M9mbrDJ7QIDkWZLSkIYjfoe1xxsr4cfngJq477mfJjv5UcFI/example2.mp4",
        "prompt": "What watch brands appear in the video?",
        "temperature": 0.4,
        "max_new_tokens": 256
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run lucataco/apollo-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "lucataco/apollo-7b:e282f76d0451b759128be3e8bccfe5ded8f521f4a7d705883e92f837e563f575",
    "input": {
      "top_p": 0.7,
      "video": "https://replicate.delivery/pbxt/M9mbrDJ7QIDkWZLSkIYjfoe1xxsr4cfngJq477mfJjv5UcFI/example2.mp4",
      "prompt": "What watch brands appear in the video?",
      "temperature": 0.4,
      "max_new_tokens": 256
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.