lucataco / apollo-3b

{
  "top_p": 0.7,
  "video": "https://replicate.delivery/pbxt/M9jsPwn8UqBPUCM6xiFEGcyfaZWXDwJ6EwcVqLPjKzcmctgn/replicate-prediction-jv0zykaqvhrmc0ckt4vtepaep4.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-3b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/apollo-3b:ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55",
  {
    input: {
      top_p: 0.7,
      video: "https://replicate.delivery/pbxt/M9jsPwn8UqBPUCM6xiFEGcyfaZWXDwJ6EwcVqLPjKzcmctgn/replicate-prediction-jv0zykaqvhrmc0ckt4vtepaep4.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-3b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/apollo-3b:ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55",
    input={
        "top_p": 0.7,
        "video": "https://replicate.delivery/pbxt/M9jsPwn8UqBPUCM6xiFEGcyfaZWXDwJ6EwcVqLPjKzcmctgn/replicate-prediction-jv0zykaqvhrmc0ckt4vtepaep4.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-3b 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-3b:ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55",
    "input": {
      "top_p": 0.7,
      "video": "https://replicate.delivery/pbxt/M9jsPwn8UqBPUCM6xiFEGcyfaZWXDwJ6EwcVqLPjKzcmctgn/replicate-prediction-jv0zykaqvhrmc0ckt4vtepaep4.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 a lone astronaut in a white spacesuit, equipped with a helmet and gloves, standing on the moon's surface. The backdrop is dominated by a large, detailed image of the moon, set against a starry space. The astronaut begins to run across the lunar terrain, leaving footprints behind. As he runs, the camera angle shifts to reveal more of the moon's rugged landscape. The astronaut continues his run until he reaches the edge of the frame, where he leaps into the vast expanse of space, floating away from the moon. Throughout the sequence, the moon remains a constant and prominent feature in the background, emphasizing the astronaut's journey into the cosmos. The video captures the astronaut's solitary trek across the moon's surface and his subsequent leap into the unknown, symbolizing humanity's boundless curiosity and spirit of exploration. The astronaut's actions are depicted with precision and grace, highlighting the beauty and isolation of space travel. The video concludes with the astronaut floating freely in space, surrounded by the endless void of space, underscoring the awe-inspiring scale and mystery of the universe. The astronaut's journey serves as a powerful metaphor for human ambition and the quest for knowledge, encapsulating the essence of space exploration. The

{
  "completed_at": "2024-12-16T20:53:39.619257Z",
  "created_at": "2024-12-16T20:52:41.083000Z",
  "data_removed": false,
  "error": null,
  "id": "65eyxmwszdrm80ckt4zajjt3rm",
  "input": {
    "top_p": 0.7,
    "video": "https://replicate.delivery/pbxt/M9jsPwn8UqBPUCM6xiFEGcyfaZWXDwJ6EwcVqLPjKzcmctgn/replicate-prediction-jv0zykaqvhrmc0ckt4vtepaep4.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": 4.283875997,
    "total_time": 58.536257
  },
  "output": "The video features a lone astronaut in a white spacesuit, equipped with a helmet and gloves, standing on the moon's surface. The backdrop is dominated by a large, detailed image of the moon, set against a starry space. The astronaut begins to run across the lunar terrain, leaving footprints behind. As he runs, the camera angle shifts to reveal more of the moon's rugged landscape. The astronaut continues his run until he reaches the edge of the frame, where he leaps into the vast expanse of space, floating away from the moon. Throughout the sequence, the moon remains a constant and prominent feature in the background, emphasizing the astronaut's journey into the cosmos. The video captures the astronaut's solitary trek across the moon's surface and his subsequent leap into the unknown, symbolizing humanity's boundless curiosity and spirit of exploration. The astronaut's actions are depicted with precision and grace, highlighting the beauty and isolation of space travel. The video concludes with the astronaut floating freely in space, surrounded by the endless void of space, underscoring the awe-inspiring scale and mystery of the universe. The astronaut's journey serves as a powerful metaphor for human ambition and the quest for knowledge, encapsulating the essence of space exploration. The",
  "started_at": "2024-12-16T20:53:35.335381Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/65eyxmwszdrm80ckt4zajjt3rm",
    "cancel": "https://api.replicate.com/v1/predictions/65eyxmwszdrm80ckt4zajjt3rm/cancel"
  },
  "version": "ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55"
}

Generated in

4.3 seconds

Tweak it Share Report

Prediction

lucataco/apollo-3b:ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55

Model

lucataco/apollo-3b:ed5ec323

fxdyrfwv65rma0ckt5csgvf0cg

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

5.5s

Created

7 months ago

Input

top_p: 0.7
video
prompt: What are the two people discussing?
temperature: 0.4
max_new_tokens: 256

{
  "top_p": 0.7,
  "video": "https://replicate.delivery/pbxt/M9kKM40Ny0vYtAprT9dMqKC6abXvGflBGBESRAQifdTnz13u/office.mp4",
  "prompt": "What are the two people discussing?",
  "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-3b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/apollo-3b:ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55",
  {
    input: {
      top_p: 0.7,
      video: "https://replicate.delivery/pbxt/M9kKM40Ny0vYtAprT9dMqKC6abXvGflBGBESRAQifdTnz13u/office.mp4",
      prompt: "What are the two people discussing?",
      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-3b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/apollo-3b:ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55",
    input={
        "top_p": 0.7,
        "video": "https://replicate.delivery/pbxt/M9kKM40Ny0vYtAprT9dMqKC6abXvGflBGBESRAQifdTnz13u/office.mp4",
        "prompt": "What are the two people discussing?",
        "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-3b 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-3b:ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55",
    "input": {
      "top_p": 0.7,
      "video": "https://replicate.delivery/pbxt/M9kKM40Ny0vYtAprT9dMqKC6abXvGflBGBESRAQifdTnz13u/office.mp4",
      "prompt": "What are the two people discussing?",
      "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 does not provide specific details about what they are discussing. However, it can be inferred that they are engaged in a professional conversation. One person is holding a pen and appears to be writing or taking notes while the other person is gesturing with their hand. The woman is also pointing towards something off-screen, indicating a possible discussion about something outside of the frame. The man is focused on his laptop, suggesting he might be referring to information displayed on the screen. Overall, the interaction seems to be a collaborative effort between the two individuals. The exact nature of their discussion is not clear from the video alone. However, based on the actions and body language, it can be inferred that they are discussing something important or significant. The woman's gestures and pointing suggest she is emphasizing a particular point or idea, while the man's focus on his laptop indicates he is considering or referencing information displayed on the screen. The overall atmosphere suggests a productive and focused discussion. The video does not provide any additional context or details about the topic being discussed. Therefore, it is difficult to determine the exact nature of their conversation. However, based on the actions and body language, it can be inferred that they are discussing something important or significant. The woman's gestures and pointing suggest she is emphasizing a

{
  "completed_at": "2024-12-16T21:22:16.369575Z",
  "created_at": "2024-12-16T21:22:10.865000Z",
  "data_removed": false,
  "error": null,
  "id": "fxdyrfwv65rma0ckt5csgvf0cg",
  "input": {
    "top_p": 0.7,
    "video": "https://replicate.delivery/pbxt/M9kKM40Ny0vYtAprT9dMqKC6abXvGflBGBESRAQifdTnz13u/office.mp4",
    "prompt": "What are the two people discussing?",
    "temperature": 0.4,
    "max_new_tokens": 256
  },
  "logs": null,
  "metrics": {
    "predict_time": 5.497270795,
    "total_time": 5.504575
  },
  "output": "The video does not provide specific details about what they are discussing. However, it can be inferred that they are engaged in a professional conversation. One person is holding a pen and appears to be writing or taking notes while the other person is gesturing with their hand. The woman is also pointing towards something off-screen, indicating a possible discussion about something outside of the frame. The man is focused on his laptop, suggesting he might be referring to information displayed on the screen. Overall, the interaction seems to be a collaborative effort between the two individuals. The exact nature of their discussion is not clear from the video alone. However, based on the actions and body language, it can be inferred that they are discussing something important or significant. The woman's gestures and pointing suggest she is emphasizing a particular point or idea, while the man's focus on his laptop indicates he is considering or referencing information displayed on the screen. The overall atmosphere suggests a productive and focused discussion. The video does not provide any additional context or details about the topic being discussed. Therefore, it is difficult to determine the exact nature of their conversation. However, based on the actions and body language, it can be inferred that they are discussing something important or significant. The woman's gestures and pointing suggest she is emphasizing a",
  "started_at": "2024-12-16T21:22:10.872304Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/fxdyrfwv65rma0ckt5csgvf0cg",
    "cancel": "https://api.replicate.com/v1/predictions/fxdyrfwv65rma0ckt5csgvf0cg/cancel"
  },
  "version": "ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55"
}

Generated in

5.5 seconds

Tweak it Share Report

Prediction

lucataco/apollo-3b:ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55

Model

lucataco/apollo-3b:ed5ec323

t7104vtxcsrmc0ckwkjvkqex4g

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

5.8s

Created

7 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/MB5r40drNs8Xb0QXuRVlmt65rWWbOkAob6suxnOsV8iVy0N7/replicate-prediction-x02cpabe8drg80ckw24t2qzwz0.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-3b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/apollo-3b:ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55",
  {
    input: {
      top_p: 0.7,
      video: "https://replicate.delivery/pbxt/MB5r40drNs8Xb0QXuRVlmt65rWWbOkAob6suxnOsV8iVy0N7/replicate-prediction-x02cpabe8drg80ckw24t2qzwz0.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-3b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/apollo-3b:ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55",
    input={
        "top_p": 0.7,
        "video": "https://replicate.delivery/pbxt/MB5r40drNs8Xb0QXuRVlmt65rWWbOkAob6suxnOsV8iVy0N7/replicate-prediction-x02cpabe8drg80ckw24t2qzwz0.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-3b 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-3b:ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55",
    "input": {
      "top_p": 0.7,
      "video": "https://replicate.delivery/pbxt/MB5r40drNs8Xb0QXuRVlmt65rWWbOkAob6suxnOsV8iVy0N7/replicate-prediction-x02cpabe8drg80ckw24t2qzwz0.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 a golden retriever dog enjoying a slice of watermelon on a wooden table. The dog is seen licking and nibbling at the juicy, red watermelon with black seeds, set against a blurred green background that suggests an outdoor setting. The dog's focused expression highlights its enjoyment of the treat. As the video progresses, the dog continues to savor the watermelon, maintaining its attention on the delicious piece in front of it. The serene and natural atmosphere underscores the dog's contentment as it relishes its meal. The video wraps up with the dog still engaged with the watermelon, emphasizing its satisfaction and delight. Throughout the clip, the dog's movements are slow and deliberate, underscoring the peaceful and enjoyable moment shared between the pet and its treat. The video concludes with the dog still holding the watermelon slice in its mouth, showcasing its contentment and satisfaction. The consistent background and the dog's actions create a cohesive narrative of a simple yet joyful moment of pet enjoyment. The video captures the essence of a relaxed and happy outdoor experience for the dog. The final frame shows the dog still holding the watermelon slice, highlighting its contentment and satisfaction. The background remains blurred, keeping the focus on the dog

{
  "completed_at": "2024-12-20T16:27:42.965966Z",
  "created_at": "2024-12-20T16:27:37.190000Z",
  "data_removed": false,
  "error": null,
  "id": "t7104vtxcsrmc0ckwkjvkqex4g",
  "input": {
    "top_p": 0.7,
    "video": "https://replicate.delivery/pbxt/MB5r40drNs8Xb0QXuRVlmt65rWWbOkAob6suxnOsV8iVy0N7/replicate-prediction-x02cpabe8drg80ckw24t2qzwz0.mp4",
    "prompt": "Describe this video in detail",
    "temperature": 0.4,
    "max_new_tokens": 256
  },
  "logs": null,
  "metrics": {
    "predict_time": 5.767927863,
    "total_time": 5.775966
  },
  "output": "The video features a golden retriever dog enjoying a slice of watermelon on a wooden table. The dog is seen licking and nibbling at the juicy, red watermelon with black seeds, set against a blurred green background that suggests an outdoor setting. The dog's focused expression highlights its enjoyment of the treat. As the video progresses, the dog continues to savor the watermelon, maintaining its attention on the delicious piece in front of it. The serene and natural atmosphere underscores the dog's contentment as it relishes its meal. The video wraps up with the dog still engaged with the watermelon, emphasizing its satisfaction and delight. Throughout the clip, the dog's movements are slow and deliberate, underscoring the peaceful and enjoyable moment shared between the pet and its treat. The video concludes with the dog still holding the watermelon slice in its mouth, showcasing its contentment and satisfaction. The consistent background and the dog's actions create a cohesive narrative of a simple yet joyful moment of pet enjoyment. The video captures the essence of a relaxed and happy outdoor experience for the dog. The final frame shows the dog still holding the watermelon slice, highlighting its contentment and satisfaction. The background remains blurred, keeping the focus on the dog",
  "started_at": "2024-12-20T16:27:37.198039Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/t7104vtxcsrmc0ckwkjvkqex4g",
    "cancel": "https://api.replicate.com/v1/predictions/t7104vtxcsrmc0ckwkjvkqex4g/cancel"
  },
  "version": "ed5ec3233f7a4331a2b0d33b8a02e62057a335e1a03107d56db9fac10cf3ce55"
}

Generated in

5.8 seconds

Tweak it Share Report