Input

image

*file

Image d'entrée (.jpg ou .png)

prompt

*string

Shift + Return to add a new line

A majestic fiery phoenix tattoo on a human back suddenly comes to life, glowing with bright orange and red flames. The flames ripple and swirl as the wings start to move. The phoenix slowly rises off the skin, lifting upward in a swirl of fire and embers. As it ascends, sparks fall around, and the wings flap powerfully. The scene is dramatic and cinematic, with a dark background and glowing light effects.A majestic fiery phoenix tattoo on a human back suddenly comes to life, glowing with bright orange and red flames. The flames ripple and swirl as the wings start to move. The phoenix slowly rises off the skin, lifting upward in a swirl of fire and embers. As it ascends, sparks fall around, and the wings flap powerfully. The scene is dramatic and cinematic, with a dark background and glowing light effects.

Prompt décrivant le mouvement

seed

integer

Seed pour la reproductibilité

Default: 42

steps

integer

Nombre d'étapes de sampling

Default: 25

duration_seconds

number

Durée de la vidéo en secondes

Default: 5

fps

integer

Framerate de sortie

Default: 30

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

npx create-replicate --model=paullux/framepack-runner

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";
import fs from "node:fs";

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

Run paullux/framepack-runner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "paullux/framepack-runner:2066ad45df0ec8d3041aa40fb18f4f14ae55154dfc85af90b41dc91c705108d8",
  {
    input: {
      fps: 30,
      seed: 42,
      image: "https://replicate.delivery/pbxt/Mz0mCaWoLbfWsu1cEq9n6cah4tkhwpURFjDubLtGWCo9SaIv/moi_tatou%C3%A9_reduce.png",
      steps: 25,
      prompt: "A majestic fiery phoenix tattoo on a human back suddenly comes to life, glowing with bright orange and red flames. The flames ripple and swirl as the wings start to move. The phoenix slowly rises off the skin, lifting upward in a swirl of fire and embers. As it ascends, sparks fall around, and the wings flap powerfully. The scene is dramatic and cinematic, with a dark background and glowing light effects.",
      duration_seconds: 5
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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 paullux/framepack-runner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "paullux/framepack-runner:2066ad45df0ec8d3041aa40fb18f4f14ae55154dfc85af90b41dc91c705108d8",
    input={
        "fps": 30,
        "seed": 42,
        "image": "https://replicate.delivery/pbxt/Mz0mCaWoLbfWsu1cEq9n6cah4tkhwpURFjDubLtGWCo9SaIv/moi_tatou%C3%A9_reduce.png",
        "steps": 25,
        "prompt": "A majestic fiery phoenix tattoo on a human back suddenly comes to life, glowing with bright orange and red flames. The flames ripple and swirl as the wings start to move. The phoenix slowly rises off the skin, lifting upward in a swirl of fire and embers. As it ascends, sparks fall around, and the wings flap powerfully. The scene is dramatic and cinematic, with a dark background and glowing light effects.",
        "duration_seconds": 5
    }
)
print(output)

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 paullux/framepack-runner 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": "paullux/framepack-runner:2066ad45df0ec8d3041aa40fb18f4f14ae55154dfc85af90b41dc91c705108d8",
    "input": {
      "fps": 30,
      "seed": 42,
      "image": "https://replicate.delivery/pbxt/Mz0mCaWoLbfWsu1cEq9n6cah4tkhwpURFjDubLtGWCo9SaIv/moi_tatou%C3%A9_reduce.png",
      "steps": 25,
      "prompt": "A majestic fiery phoenix tattoo on a human back suddenly comes to life, glowing with bright orange and red flames. The flames ripple and swirl as the wings start to move. The phoenix slowly rises off the skin, lifting upward in a swirl of fire and embers. As it ascends, sparks fall around, and the wings flap powerfully. The scene is dramatic and cinematic, with a dark background and glowing light effects.",
      "duration_seconds": 5
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-05-10T08:03:37.622216Z",
  "created_at": "2025-05-10T07:37:12.305000Z",
  "data_removed": false,
  "error": null,
  "id": "0ew5xpvde5rj40cpq4gb1vm2aw",
  "input": {
    "fps": 30,
    "seed": 42,
    "image": "https://replicate.delivery/pbxt/Mz0mCaWoLbfWsu1cEq9n6cah4tkhwpURFjDubLtGWCo9SaIv/moi_tatou%C3%A9_reduce.png",
    "steps": 25,
    "prompt": "A majestic fiery phoenix tattoo on a human back suddenly comes to life, glowing with bright orange and red flames. The flames ripple and swirl as the wings start to move. The phoenix slowly rises off the skin, lifting upward in a swirl of fire and embers. As it ascends, sparks fall around, and the wings flap powerfully. The scene is dramatic and cinematic, with a dark background and glowing light effects.",
    "duration_seconds": 5
  },
  "logs": "📸 Chargement de l’image depuis /tmp/tmpnlks0_8pmoi_tatoué_reduce.png\n🧠 Encodage CLIP Vision...\n🧠 Encodage VAE...\n🧠 Encodage du prompt...\n🎞️ Sampling...\n  0%|          | 0/25 [00:00<?, ?it/s]\n  4%|▍         | 1/25 [00:19<07:57, 19.91s/it]\n  8%|▊         | 2/25 [00:33<06:14, 16.29s/it]\n 12%|█▏        | 3/25 [00:53<06:35, 17.98s/it]\n 16%|█▌        | 4/25 [01:13<06:34, 18.78s/it]\n 20%|██        | 5/25 [01:33<06:24, 19.21s/it]\n 24%|██▍       | 6/25 [01:53<06:10, 19.48s/it]\n 28%|██▊       | 7/25 [02:13<05:53, 19.64s/it]\n 32%|███▏      | 8/25 [02:33<05:35, 19.75s/it]\n 36%|███▌      | 9/25 [02:53<05:17, 19.82s/it]\n 40%|████      | 10/25 [03:13<04:58, 19.87s/it]\n 44%|████▍     | 11/25 [03:33<04:38, 19.90s/it]\n 48%|████▊     | 12/25 [03:53<04:19, 19.92s/it]\n 52%|█████▏    | 13/25 [04:13<03:59, 19.94s/it]\n 56%|█████▌    | 14/25 [04:33<03:39, 19.95s/it]\n 60%|██████    | 15/25 [04:53<03:19, 19.96s/it]\n 64%|██████▍   | 16/25 [05:13<02:59, 19.96s/it]\n 68%|██████▊   | 17/25 [05:33<02:39, 19.96s/it]\n 72%|███████▏  | 18/25 [05:53<02:19, 19.96s/it]\n 76%|███████▌  | 19/25 [06:13<01:59, 19.95s/it]\n 80%|████████  | 20/25 [06:33<01:39, 19.95s/it]\n 84%|████████▍ | 21/25 [06:53<01:19, 19.95s/it]\n 88%|████████▊ | 22/25 [07:13<00:59, 19.95s/it]\n 92%|█████████▏| 23/25 [07:33<00:39, 19.95s/it]\n 96%|█████████▌| 24/25 [07:52<00:19, 19.94s/it]\n100%|██████████| 25/25 [08:12<00:00, 19.94s/it]\n100%|██████████| 25/25 [08:12<00:00, 19.72s/it]\n🖼️ Décodage final...\n🎬 Vidéo enregistrée à /tmp/tmp3rq4_roc.mp4",
  "metrics": {
    "predict_time": 530.533358805,
    "total_time": 1585.317216
  },
  "output": "https://replicate.delivery/yhqm/Z6we9S1eFEjYKkKjcH3XYElHZy1pMB7uuTs7iXPe7xcySXWpA/tmp3rq4_roc.mp4",
  "started_at": "2025-05-10T07:54:47.088857Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/qoxq-efazfxg2njlcvoijzrf47yxp7sg6ngzlozv3jcsbtajspecpfwha",
    "get": "https://api.replicate.com/v1/predictions/0ew5xpvde5rj40cpq4gb1vm2aw",
    "cancel": "https://api.replicate.com/v1/predictions/0ew5xpvde5rj40cpq4gb1vm2aw/cancel"
  },
  "version": "2066ad45df0ec8d3041aa40fb18f4f14ae55154dfc85af90b41dc91c705108d8"
}

Generated in

8 minutes 51 seconds

Tweak it Share Report View full prediction

Examples

View more examples

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

🎞️ FramePack Runner – Image-to-Video with Prompt

Generate short videos from a single image and a motion prompt using the FramePack architecture by Stanford (2025).

👉 Try it now on Replicate

✨ Example usage

replicate run paullux/framepack-runner \
  -v image=@input.png \
  -v prompt="A cat jumps backward in surprise" \
  -v seed=123 \
  -v steps=30 \
  -v duration_seconds=5 \
  -v fps=30

🧠 About FramePack

Packing Input Frame Contexts in Next-Frame Prediction Models for Video Generation Lvmin Zhang, Maneesh Agrawala – Stanford University, 2025

FramePack compresses temporal context into fixed-length representations, making it highly efficient for generating long video sequences.

📄 Project page
🧪 Uses the FramePackPipeline from 🤗 diffusers

📦 Inputs

Name	Type	Description
`image`	`file`	The input image (`.png` or `.jpg`)
`prompt`	`string`	A motion-focused description prompt
`seed`	`integer`	Random seed for reproducibility (default: `42`)
`steps`	`integer`	Sampling steps (default: `25`)
`duration_seconds`	`number`	Duration of the video in seconds (default: `5`)
`fps`	`integer`	Output video frame rate (default: `30`)

📤 Output

Returns an .mp4 video file composed of all generated frames.

🛠 How it works

python framepack_runner.py \
  -v image=@input.png \
  -v prompt="A cat jumps backward in surprise" \
  -v seed=123 \
  -v steps=30 \
  -v duration_seconds=5 \
  -v fps=30

All frames are saved locally and then compiled into a video using ffmpeg.

📸 Example Prompt Ideas

The robot jumps forward and transforms mid-air.
A woman spins slowly in a dark room, lit by candlelight.
The camera zooms toward a cat staring at a moving shadow.

📃 License

This implementation uses FramePack under its original academic license. Your usage of Replicate infrastructure is bound by their terms of service.

🙌 Credits

Based on FramePack by Lvmin Zhang & Maneesh Agrawala (Stanford).

paullux / framepack-runner

Input

Output

Examples

Run time and cost

Readme

🎞️ FramePack Runner – Image-to-Video with Prompt

✨ Example usage

🧠 About FramePack

📦 Inputs

📤 Output

🛠 How it works

📸 Example Prompt Ideas

📃 License

🙌 Credits

Logs (0ew5xpvde5rj40cpq4gb1vm2aw)