Prediction

meta/meta-llama-3.1-405b-instruct

Official model

meta/meta-llama-3.1-405b-instruct

w1gdknd8asrm00chmmqsnthap0

Status

Succeeded

Source

Web

Total duration

22.4s

Created

8 months ago by @zeke

Input

top_p: 0.9
prompt: Write ten prompts for an image generation model. The prompts should describe a fictitious person named ZIKI in various scenarios. Make sure to use the word ZIKI in all caps in every prompt. Make the prompts highly detailed and interesting, and make them varied in subject matter. Make sure the prompts will generate images that include unobscured facial details. ZIKI is a 43 year old adult male. Include some reference to this in prompt to avoid misrepresenting ZIKI’s age or gender. Do not allude to ZIKI’s eye color.
max_tokens: 1024
min_tokens: 0
temperature: 0.6
system_prompt: You are a helpful assistant.
presence_penalty: 0
frequency_penalty: 0

{
  "top_p": 0.9,
  "prompt": "Write ten prompts for an image generation model. The prompts should describe a fictitious person named ZIKI in various scenarios. Make sure to use the word ZIKI in all caps in every prompt. Make the prompts highly detailed and interesting, and make them varied in subject matter. Make sure the prompts will generate images that include unobscured facial details. ZIKI is a 43 year old adult male. Include some reference to this in prompt to avoid misrepresenting ZIKI’s age or gender. Do not allude to ZIKI’s eye color.",
  "max_tokens": 1024,
  "min_tokens": 0,
  "temperature": 0.6,
  "system_prompt": "You are a helpful assistant.",
  "presence_penalty": 0,
  "frequency_penalty": 0
}

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 meta/meta-llama-3.1-405b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  top_p: 0.9,
  prompt: "Write ten prompts for an image generation model. The prompts should describe a fictitious person named ZIKI in various scenarios. Make sure to use the word ZIKI in all caps in every prompt. Make the prompts highly detailed and interesting, and make them varied in subject matter. Make sure the prompts will generate images that include unobscured facial details. ZIKI is a 43 year old adult male. Include some reference to this in prompt to avoid misrepresenting ZIKI’s age or gender. Do not allude to ZIKI’s eye color.",
  max_tokens: 1024,
  min_tokens: 0,
  temperature: 0.6,
  system_prompt: "You are a helpful assistant.",
  presence_penalty: 0,
  frequency_penalty: 0
};

for await (const event of replicate.stream("meta/meta-llama-3.1-405b-instruct", { input })) {
  process.stdout.write(event.toString());
};

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 meta/meta-llama-3.1-405b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

# The meta/meta-llama-3.1-405b-instruct model can stream output as it's running.
for event in replicate.stream(
    "meta/meta-llama-3.1-405b-instruct",
    input={
        "top_p": 0.9,
        "prompt": "Write ten prompts for an image generation model. The prompts should describe a fictitious person named ZIKI in various scenarios. Make sure to use the word ZIKI in all caps in every prompt. Make the prompts highly detailed and interesting, and make them varied in subject matter. Make sure the prompts will generate images that include unobscured facial details. ZIKI is a 43 year old adult male. Include some reference to this in prompt to avoid misrepresenting ZIKI’s age or gender. Do not allude to ZIKI’s eye color.",
        "max_tokens": 1024,
        "min_tokens": 0,
        "temperature": 0.6,
        "system_prompt": "You are a helpful assistant.",
        "presence_penalty": 0,
        "frequency_penalty": 0
    },
):
    print(str(event), 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 meta/meta-llama-3.1-405b-instruct 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 $'{
    "input": {
      "top_p": 0.9,
      "prompt": "Write ten prompts for an image generation model. The prompts should describe a fictitious person named ZIKI in various scenarios. Make sure to use the word ZIKI in all caps in every prompt. Make the prompts highly detailed and interesting, and make them varied in subject matter. Make sure the prompts will generate images that include unobscured facial details. ZIKI is a 43 year old adult male. Include some reference to this in prompt to avoid misrepresenting ZIKI’s age or gender. Do not allude to ZIKI’s eye color.",
      "max_tokens": 1024,
      "min_tokens": 0,
      "temperature": 0.6,
      "system_prompt": "You are a helpful assistant.",
      "presence_penalty": 0,
      "frequency_penalty": 0
    }
  }' \
  https://api.replicate.com/v1/models/meta/meta-llama-3.1-405b-instruct/predictions

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

Output

Here are ten prompts for an image generation model featuring ZIKI in various scenarios: 1. **ZIKI**, a 43-year-old man with a rugged beard, stands triumphantly atop a snow-capped mountain, his weathered face creased with a warm smile as he gazes out at the breathtaking sunrise, his bright orange jacket and gloves a stark contrast to the icy landscape. 2. In a dimly lit, smoke-filled jazz club, **ZIKI** sits at the piano, his eyes closed in concentration as he improvises a soulful melody, his graying hair slicked back, revealing a prominent widow's peak, while his slender fingers dance across the keys. 3. Wearing a crisp white apron, **ZIKI** expertly flips a sizzling pancake in a bustling diner kitchen, his 43-year-old face flushed from the heat, a sprinkle of flour dusting his nose, as he flashes a cheerful grin at a coworker. 4. **ZIKI**, dressed in a sleek black tuxedo, stands confidently at the podium of a grand auditorium, his voice booming as he delivers a passionate speech, his mature features illuminated by the soft glow of the stage lights. 5. In a serene, candlelit yoga studio, **ZIKI** balances effortlessly in tree pose, his eyes focused inward, his weathered skin glowing with a warm, golden light, as he exhales a gentle breath, his graying hair tied back in a ponytail. 6. **ZIKI**, clad in a worn leather jacket, strums a power chord on his electric guitar in a cramped, graffiti-covered music studio, his 43-year-old face set in a fierce expression, as he loses himself in the raw energy of the music. 7. Surrounded by vibrant, exotic flowers, **ZIKI** tends to his lush garden, his face creased with a gentle smile as he inspects a particularly radiant bloom, his mature features softened by the warm sunlight and gentle colors. 8. **ZIKI**, dressed in a crisp, navy blue business suit, sits at the head of a sleek, modern conference table, his eyes locked intently on a colleague as he leads a high-stakes meeting, his 43-year-old face a picture of confident authority. 9. In a cozy, book-lined study, **ZIKI** sits in a worn, leather armchair, his eyes lost in the pages of a dog-eared novel, his graying hair mussed, as he sips a steaming cup of coffee, a look of quiet contemplation on his mature face. 10. **ZIKI**, wearing a bright, Hawaiian shirt, laughs joyfully as he spins a colorful, hand-painted ceramic plate in a sun-drenched pottery studio, his 43-year-old face aglow with creative enthusiasm, as he shares a moment of artistic triumph with a fellow craftsperson.

{
  "completed_at": "2024-08-30T21:27:52.028132Z",
  "created_at": "2024-08-30T21:27:29.622000Z",
  "data_removed": false,
  "error": null,
  "id": "w1gdknd8asrm00chmmqsnthap0",
  "input": {
    "top_p": 0.9,
    "prompt": "Write ten prompts for an image generation model. The prompts should describe a fictitious person named ZIKI in various scenarios. Make sure to use the word ZIKI in all caps in every prompt. Make the prompts highly detailed and interesting, and make them varied in subject matter. Make sure the prompts will generate images that include unobscured facial details. ZIKI is a 43 year old adult male. Include some reference to this in prompt to avoid misrepresenting ZIKI’s age or gender. Do not allude to ZIKI’s eye color.",
    "max_tokens": 1024,
    "min_tokens": 0,
    "temperature": 0.6,
    "system_prompt": "You are a helpful assistant.",
    "presence_penalty": 0,
    "frequency_penalty": 0
  },
  "logs": "Generation took 1725050758.02sFormatted prompt: <|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWrite ten prompts for an image generation model. The prompts should describe a fictitious person named ZIKI in various scenarios. Make sure to use the word ZIKI in all caps in every prompt. Make the prompts highly detailed and interesting, and make them varied in subject matter. Make sure the prompts will generate images that include unobscured facial details. ZIKI is a 43 year old adult male. Include some reference to this in prompt to avoid misrepresenting ZIKI’s age or gender. Do not allude to ZIKI’s eye color.<|eot_id|><|start_header_id|>assistant<|end_header_id|>",
  "metrics": {
    "batch_size": 5.285750068072575,
    "input_token_count": 124,
    "tokens_per_second": 26.977442858879424,
    "output_token_count": 602,
    "predict_time_share": 4.237674258436476,
    "predict_time": 22.401641707,
    "total_time": 22.406132,
    "time_to_first_token": 0.09119240199999999
  },
  "output": [
    "Here",
    " are",
    " ten",
    " prompts",
    " for",
    " an",
    " image",
    " generation",
    " model",
    " featuring",
    " Z",
    "IK",
    "I",
    " in",
    " various",
    " scenarios",
    ":\n\n",
    "1",
    ".",
    " **",
    "Z",
    "IK",
    "I",
    "**,",
    " a",
    " ",
    "43",
    "-year",
    "-old",
    " man",
    " with",
    " a",
    " rugged",
    " beard",
    ",",
    " stands",
    " triumph",
    "antly",
    " atop",
    " a",
    " snow",
    "-c",
    "apped",
    " mountain",
    ",",
    " his",
    " weather",
    "ed",
    " face",
    " cre",
    "ased",
    " with",
    " a",
    " warm",
    " smile",
    " as",
    " he",
    " gaz",
    "es",
    " out",
    " at",
    " the",
    " breathtaking",
    " sunrise",
    ",",
    " his",
    " bright",
    " orange",
    " jacket",
    " and",
    " gloves",
    " a",
    " stark",
    " contrast",
    " to",
    " the",
    " icy",
    " landscape",
    ".\n",
    "2",
    ".",
    " In",
    " a",
    " dim",
    "ly",
    " lit",
    ",",
    " smoke",
    "-filled",
    " jazz",
    " club",
    ",",
    " **",
    "Z",
    "IK",
    "I",
    "**",
    " sits",
    " at",
    " the",
    " piano",
    ",",
    " his",
    " eyes",
    " closed",
    " in",
    " concentration",
    " as",
    " he",
    " improvis",
    "es",
    " a",
    " soul",
    "ful",
    " melody",
    ",",
    " his",
    " gr",
    "aying",
    " hair",
    " slick",
    "ed",
    " back",
    ",",
    " revealing",
    " a",
    " prominent",
    " widow",
    "'s",
    " peak",
    ",",
    " while",
    " his",
    " slender",
    " fingers",
    " dance",
    " across",
    " the",
    " keys",
    ".\n",
    "3",
    ".",
    " W",
    "earing",
    " a",
    " crisp",
    " white",
    " apr",
    "on",
    ",",
    " **",
    "Z",
    "IK",
    "I",
    "**",
    " expert",
    "ly",
    " flips",
    " a",
    " s",
    "izzling",
    " panc",
    "ake",
    " in",
    " a",
    " bustling",
    " diner",
    " kitchen",
    ",",
    " his",
    " ",
    "43",
    "-year",
    "-old",
    " face",
    " flushed",
    " from",
    " the",
    " heat",
    ",",
    " a",
    " sprinkle",
    " of",
    " flour",
    " dust",
    "ing",
    " his",
    " nose",
    ",",
    " as",
    " he",
    " flashes",
    " a",
    " cheerful",
    " grin",
    " at",
    " a",
    " cowork",
    "er",
    ".\n",
    "4",
    ".",
    " **",
    "Z",
    "IK",
    "I",
    "**,",
    " dressed",
    " in",
    " a",
    " sleek",
    " black",
    " t",
    "ux",
    "edo",
    ",",
    " stands",
    " confidently",
    " at",
    " the",
    " podium",
    " of",
    " a",
    " grand",
    " auditor",
    "ium",
    ",",
    " his",
    " voice",
    " booming",
    " as",
    " he",
    " delivers",
    " a",
    " passionate",
    " speech",
    ",",
    " his",
    " mature",
    " features",
    " illuminated",
    " by",
    " the",
    " soft",
    " glow",
    " of",
    " the",
    " stage",
    " lights",
    ".\n",
    "5",
    ".",
    " In",
    " a",
    " serene",
    ",",
    " candle",
    "lit",
    " yoga",
    " studio",
    ",",
    " **",
    "Z",
    "IK",
    "I",
    "**",
    " balances",
    " effortlessly",
    " in",
    " tree",
    " pose",
    ",",
    " his",
    " eyes",
    " focused",
    " inward",
    ",",
    " his",
    " weather",
    "ed",
    " skin",
    " glowing",
    " with",
    " a",
    " warm",
    ",",
    " golden",
    " light",
    ",",
    " as",
    " he",
    " exh",
    "ales",
    " a",
    " gentle",
    " breath",
    ",",
    " his",
    " gr",
    "aying",
    " hair",
    " tied",
    " back",
    " in",
    " a",
    " pony",
    "tail",
    ".\n",
    "6",
    ".",
    " **",
    "Z",
    "IK",
    "I",
    "**,",
    " clad",
    " in",
    " a",
    " worn",
    " leather",
    " jacket",
    ",",
    " str",
    "ums",
    " a",
    " power",
    " chord",
    " on",
    " his",
    " electric",
    " guitar",
    " in",
    " a",
    " cramped",
    ",",
    " graffiti",
    "-covered",
    " music",
    " studio",
    ",",
    " his",
    " ",
    "43",
    "-year",
    "-old",
    " face",
    " set",
    " in",
    " a",
    " fierce",
    " expression",
    ",",
    " as",
    " he",
    " loses",
    " himself",
    " in",
    " the",
    " raw",
    " energy",
    " of",
    " the",
    " music",
    ".\n",
    "7",
    ".",
    " Sur",
    "rounded",
    " by",
    " vibrant",
    ",",
    " exotic",
    " flowers",
    ",",
    " **",
    "Z",
    "IK",
    "I",
    "**",
    " tends",
    " to",
    " his",
    " lush",
    " garden",
    ",",
    " his",
    " face",
    " cre",
    "ased",
    " with",
    " a",
    " gentle",
    " smile",
    " as",
    " he",
    " ins",
    "pects",
    " a",
    " particularly",
    " radiant",
    " bloom",
    ",",
    " his",
    " mature",
    " features",
    " softened",
    " by",
    " the",
    " warm",
    " sunlight",
    " and",
    " gentle",
    " colors",
    ".\n",
    "8",
    ".",
    " **",
    "Z",
    "IK",
    "I",
    "**,",
    " dressed",
    " in",
    " a",
    " crisp",
    ",",
    " navy",
    " blue",
    " business",
    " suit",
    ",",
    " sits",
    " at",
    " the",
    " head",
    " of",
    " a",
    " sleek",
    ",",
    " modern",
    " conference",
    " table",
    ",",
    " his",
    " eyes",
    " locked",
    " int",
    "ently",
    " on",
    " a",
    " colleague",
    " as",
    " he",
    " leads",
    " a",
    " high",
    "-st",
    "akes",
    " meeting",
    ",",
    " his",
    " ",
    "43",
    "-year",
    "-old",
    " face",
    " a",
    " picture",
    " of",
    " confident",
    " authority",
    ".\n",
    "9",
    ".",
    " In",
    " a",
    " cozy",
    ",",
    " book",
    "-lined",
    " study",
    ",",
    " **",
    "Z",
    "IK",
    "I",
    "**",
    " sits",
    " in",
    " a",
    " worn",
    ",",
    " leather",
    " arm",
    "chair",
    ",",
    " his",
    " eyes",
    " lost",
    " in",
    " the",
    " pages",
    " of",
    " a",
    " dog",
    "-e",
    "ared",
    " novel",
    ",",
    " his",
    " gr",
    "aying",
    " hair",
    " muss",
    "ed",
    ",",
    " as",
    " he",
    " s",
    "ips",
    " a",
    " ste",
    "aming",
    " cup",
    " of",
    " coffee",
    ",",
    " a",
    " look",
    " of",
    " quiet",
    " contempl",
    "ation",
    " on",
    " his",
    " mature",
    " face",
    ".\n",
    "10",
    ".",
    " **",
    "Z",
    "IK",
    "I",
    "**,",
    " wearing",
    " a",
    " bright",
    ",",
    " Hawaiian",
    " shirt",
    ",",
    " laughs",
    " joy",
    "fully",
    " as",
    " he",
    " spins",
    " a",
    " colorful",
    ",",
    " hand",
    "-p",
    "ainted",
    " ceramic",
    " plate",
    " in",
    " a",
    " sun",
    "-d",
    "renched",
    " pottery",
    " studio",
    ",",
    " his",
    " ",
    "43",
    "-year",
    "-old",
    " face",
    " ag",
    "low",
    " with",
    " creative",
    " enthusiasm",
    ",",
    " as",
    " he",
    " shares",
    " a",
    " moment",
    " of",
    " artistic",
    " triumph",
    " with",
    " a",
    " fellow",
    " craft",
    "sp",
    "erson",
    ".",
    ""
  ],
  "started_at": "2024-08-30T21:27:29.626490Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream-b.svc.sea.v.replicate.net/v1/streams/anpf54h3q4wyv7wmqfzthet3ftyjw7ekedqtmsqdeh7nglsvydaq",
    "get": "https://api.replicate.com/v1/predictions/w1gdknd8asrm00chmmqsnthap0",
    "cancel": "https://api.replicate.com/v1/predictions/w1gdknd8asrm00chmmqsnthap0/cancel"
  },
  "version": "hidden"
}

Generated in

22.4 seconds

Input tokens

120

Output tokens

600

Tokens per second

26.98 tokens / second

Time to first token

91 milliseconds

Tweak it Report