hayooucom/vision-model2 | Run with an API on Replicate

hayooucom

vision-model2

Cold

welcome to contact us. youkpan@gmail.com

Public

346 runs

L40S

Run with an API

Pricing

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Text prompt to send to the model.

Default: "Describe this."

full_prompt

string

Shift + Return to add a new line

full prompt to send to the model. if use this ,set prompt to empty

Default: ""

max_new_tokens

integer

(minimum: 1, maximum: 8000)

Maximum number of tokens to generate. A word is generally 2-3 tokens.

Default: 200

temperature

number

(minimum: 0, maximum: 5)

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic.

Default: 0.1

top_p

number

(minimum: 0.01, maximum: 1)

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens.

Default: 0.95

top_k

integer

When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens.

Default: 5

repetition_penalty

number

(minimum: 0.01, maximum: 10)

Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.

Default: 1.1

system_prompt

string

Shift + Return to add a new line

You are agent that can see, talk and act.You are agent that can see, talk and act.

System prompt.

Default: "You are agent that can see, talk and act."

image_url0

string

Shift + Return to add a new line

public image url.

Default: ""

image_url

string[]

https://v.stylee.top/files/test.jpg

public image url.

Default: []

image_base64

string[]

image data base64 if no image url, use this.

Default: []

seed

integer

The seed for the random number generator

output_id_as_str

integer

output id as string

Default: 0

Run this model in Node.js with one line of code:

npx create-replicate --model=hayooucom/vision-model2

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

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

Run hayooucom/vision-model2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "hayooucom/vision-model2:29e97c56ac1a0344a96dcbcf1d7f1e363279910aa61fdb91d9c333c9e223ab41",
  {
    input: {
      seed: 123123,
      top_k: 5,
      top_p: 0.95,
      prompt: "Describe this.",
      image_url: ["https://v.stylee.top/files/test.jpg"],
      image_url0: "",
      full_prompt: "",
      temperature: 0.15,
      image_base64: [],
      system_prompt: "You are agent that can see, talk and act.",
      max_new_tokens: 912,
      output_id_as_str: 0,
      repetition_penalty: 1.1
    }
  }
);

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run hayooucom/vision-model2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "hayooucom/vision-model2:29e97c56ac1a0344a96dcbcf1d7f1e363279910aa61fdb91d9c333c9e223ab41",
    input={
        "seed": 123123,
        "top_k": 5,
        "top_p": 0.95,
        "prompt": "Describe this.",
        "image_url": ["https://v.stylee.top/files/test.jpg"],
        "image_url0": "",
        "full_prompt": "",
        "temperature": 0.15,
        "image_base64": [],
        "system_prompt": "You are agent that can see, talk and act.",
        "max_new_tokens": 912,
        "output_id_as_str": 0,
        "repetition_penalty": 1.1
    }
)

# The hayooucom/vision-model2 model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/hayooucom/vision-model2/api#output-schema
    print(item, end="")

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run hayooucom/vision-model2 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": "hayooucom/vision-model2:29e97c56ac1a0344a96dcbcf1d7f1e363279910aa61fdb91d9c333c9e223ab41",
    "input": {
      "seed": 123123,
      "top_k": 5,
      "top_p": 0.95,
      "prompt": "Describe this.",
      "image_url": ["https://v.stylee.top/files/test.jpg"],
      "image_url0": "",
      "full_prompt": "",
      "temperature": 0.15,
      "image_base64": [],
      "system_prompt": "You are agent that can see, talk and act.",
      "max_new_tokens": 912,
      "output_id_as_str": 0,
      "repetition_penalty": 1.1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

The image captures a moment of tranquility, featuring a black smartwatch resting on a wooden surface. The watch, which is the central focus of the image, is connected to a white charging cable. The cable, coiled and ready for use, extends from the watch, suggesting it's in the process of being charged. The screen of the watch is alive with text, providing information about the "AI Friend" necklace. This suggests that the watch might be connected to a virtual assistant or a piece of wearable technology. The text on the screen reads: "The AI Friend necklace is a new wearable tech designed to act as a virtual friend. It's a virtual friend that you wear like a necklace." The background of the image is blurred, drawing the viewer's attention to the watch and its charging cable. The wooden surface on which the watch rests adds a touch of warmth to the scene. The overall composition of the image suggests a blend of technology and simplicity.

{
  "completed_at": "2025-02-27T19:01:53.807193Z",
  "created_at": "2025-02-27T18:54:13.323000Z",
  "data_removed": false,
  "error": null,
  "id": "6dyw9tk19drm80cn9319v2mbsw",
  "input": {
    "seed": 123123,
    "top_k": 5,
    "top_p": 0.95,
    "prompt": "Describe this.",
    "image_url": [
      "https://v.stylee.top/files/test.jpg"
    ],
    "image_url0": "",
    "full_prompt": "",
    "temperature": 0.15,
    "image_base64": [],
    "system_prompt": "You are agent that can see, talk and act.",
    "max_new_tokens": 912,
    "repetition_penalty": 1.1
  },
  "logs": "/root/.pyenv/versions/3.12.9/lib/python3.12/site-packages/transformers/generation/configuration_utils.py:628: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.15` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.\nwarnings.warn(\n/root/.pyenv/versions/3.12.9/lib/python3.12/site-packages/transformers/generation/configuration_utils.py:633: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.95` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.\nwarnings.warn(\n/root/.pyenv/versions/3.12.9/lib/python3.12/site-packages/torch/_dynamo/eval_frame.py:745: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.5 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\nreturn fn(*args, **kwargs)\n/root/.pyenv/versions/3.12.9/lib/python3.12/site-packages/torch/utils/checkpoint.py:87: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\nwarnings.warn(\nThe `seen_tokens` attribute is deprecated and will be removed in v4.41. Use the `cache_position` model input instead.\nFrom v4.47 onwards, when a model cache is to be returned, `generate` will return a `Cache` instance instead by default (as opposed to the legacy tuple of tuples format). If you want to keep returning the legacy format, please set `return_legacy_cache=True`.",
  "metrics": {
    "predict_time": 8.779144527,
    "total_time": 460.484193
  },
  "output": [
    "",
    "The ",
    "image ",
    "captures ",
    "a ",
    "moment ",
    "of ",
    "",
    "",
    "tranquility, ",
    "featuring ",
    "a ",
    "black ",
    "",
    "smartwatch ",
    "resting ",
    "on ",
    "a ",
    "wooden ",
    "",
    "surface. ",
    "The ",
    "",
    "watch, ",
    "which ",
    "is ",
    "the ",
    "central ",
    "focus ",
    "of ",
    "the ",
    "",
    "image, ",
    "is ",
    "connected ",
    "to ",
    "a ",
    "white ",
    "charging ",
    "",
    "cable. ",
    "The ",
    "",
    "cable, ",
    "",
    "coiled ",
    "and ",
    "ready ",
    "for ",
    "",
    "use, ",
    "extends ",
    "from ",
    "the ",
    "",
    "watch, ",
    "suggesting ",
    "",
    "it's ",
    "in ",
    "the ",
    "process ",
    "of ",
    "being ",
    "charged.\n\n",
    "",
    "The ",
    "screen ",
    "of ",
    "the ",
    "watch ",
    "is ",
    "alive ",
    "with ",
    "",
    "text, ",
    "providing ",
    "information ",
    "about ",
    "the ",
    "",
    "\"AI ",
    "",
    "Friend\" ",
    "",
    "necklace. ",
    "This ",
    "suggests ",
    "that ",
    "the ",
    "watch ",
    "might ",
    "be ",
    "connected ",
    "to ",
    "a ",
    "virtual ",
    "assistant ",
    "or ",
    "a ",
    "piece ",
    "of ",
    "wearable ",
    "",
    "technology. ",
    "The ",
    "text ",
    "on ",
    "the ",
    "screen ",
    "",
    "reads: ",
    "",
    "\"The ",
    "AI ",
    "Friend ",
    "necklace ",
    "is ",
    "a ",
    "new ",
    "wearable ",
    "tech ",
    "designed ",
    "to ",
    "act ",
    "as ",
    "a ",
    "virtual ",
    "",
    "friend. ",
    "",
    "It's ",
    "a ",
    "virtual ",
    "friend ",
    "that ",
    "you ",
    "wear ",
    "like ",
    "a ",
    "necklace.\"\n\n",
    "",
    "The ",
    "background ",
    "of ",
    "the ",
    "image ",
    "is ",
    "",
    "blurred, ",
    "drawing ",
    "the ",
    "",
    "viewer's ",
    "attention ",
    "to ",
    "the ",
    "watch ",
    "and ",
    "its ",
    "charging ",
    "",
    "cable. ",
    "The ",
    "wooden ",
    "surface ",
    "on ",
    "which ",
    "the ",
    "watch ",
    "rests ",
    "adds ",
    "a ",
    "touch ",
    "of ",
    "warmth ",
    "to ",
    "the ",
    "",
    "scene. ",
    "The ",
    "overall ",
    "composition ",
    "of ",
    "the ",
    "image ",
    "suggests ",
    "a ",
    "blend ",
    "of ",
    "technology ",
    "and ",
    "",
    "",
    "simplicity."
  ],
  "started_at": "2025-02-27T19:01:45.028049Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream-b.svc.ric1.c.replicate.net/v1/streams/y7kbmfqhdydjzzoysu3j2dil5dt35mpzdrgfulfo6e574d7kgvuq",
    "get": "https://api.replicate.com/v1/predictions/6dyw9tk19drm80cn9319v2mbsw",
    "cancel": "https://api.replicate.com/v1/predictions/6dyw9tk19drm80cn9319v2mbsw/cancel"
  },
  "version": "13fae1f2dff4d16bb15793c3d2de3d3fe6800f0faed6dd279086c337246a5761"
}

Generated in

8.8 seconds

Tweak it Iterate in playground Share Report View full prediction

This output was created using a different version of the model, hayooucom/vision-model2:13fae1f2.

Run time and cost

This model costs approximately $0.0021 to run on Replicate, or 476 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 3 seconds.

Readme

This model doesn't have a readme.