genmoai/mochi-1-lora:bad496d8 | Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

genmoai /mochi-1-lora:bad496d8

Input

prompt

string

Shift + Return to add a new line

gingerbread man is dancing on a table. melty.gingerbread man is dancing on a table. melty.

Focus on a single, central subject. Structure the prompt from coarse to fine details. Start with 'a close shot' or 'a medium shot' if applicable. Append 'high resolution 4k' to reduce warping

Default: "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."

num_frames

integer

(minimum: 30, maximum: 170)

Number of frames to generate

Default: 163

num_inference_steps

integer

(minimum: 10, maximum: 200)

Number of inference steps

Default: 64

guidance_scale

number

(minimum: 0.1, maximum: 10)

The guidance scale for the model

Default: 6

fps

integer

(minimum: 10, maximum: 60)

Frames per second

Default: 30

hf_lora

string

Shift + Return to add a new line

Hugging face LoRa

lora_scale

number

LoRa scale

Default: 1

seed

integer

Random seed

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

npx create-replicate --model=genmoai/mochi-1-lora

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 genmoai/mochi-1-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "genmoai/mochi-1-lora:bad496d88086d5f60307291a512fdcb4fab0b30027e7ccbcc2ecf5e6606d5e20",
  {
    input: {
      fps: 24,
      seed: 47731,
      prompt: "gingerbread man is dancing on a table. melty.",
      hf_lora: "lucataco/mochi-lora-melty",
      lora_scale: 1,
      num_frames: 121,
      guidance_scale: 6,
      num_inference_steps: 30
    }
  }
);

// 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 genmoai/mochi-1-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "genmoai/mochi-1-lora:bad496d88086d5f60307291a512fdcb4fab0b30027e7ccbcc2ecf5e6606d5e20",
    input={
        "fps": 24,
        "seed": 47731,
        "prompt": "gingerbread man is dancing on a table. melty.",
        "hf_lora": "lucataco/mochi-lora-melty",
        "lora_scale": 1,
        "num_frames": 121,
        "guidance_scale": 6,
        "num_inference_steps": 30
    }
)
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 genmoai/mochi-1-lora 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": "genmoai/mochi-1-lora:bad496d88086d5f60307291a512fdcb4fab0b30027e7ccbcc2ecf5e6606d5e20",
    "input": {
      "fps": 24,
      "seed": 47731,
      "prompt": "gingerbread man is dancing on a table. melty.",
      "hf_lora": "lucataco/mochi-lora-melty",
      "lora_scale": 1,
      "num_frames": 121,
      "guidance_scale": 6,
      "num_inference_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-12-12T21:47:08.326358Z",
  "created_at": "2024-12-12T21:42:20.993000Z",
  "data_removed": false,
  "error": null,
  "id": "42wspzx285rmc0ckqk99tdda7w",
  "input": {
    "fps": 24,
    "seed": 47731,
    "prompt": "gingerbread man is dancing on a table. melty.",
    "hf_lora": "lucataco/mochi-lora-melty",
    "lora_scale": 1,
    "num_frames": 121,
    "guidance_scale": 6,
    "num_inference_steps": 30
  },
  "logs": "Using seed: 47731\nLoading LoRA: lucataco/mochi-lora-melty with scale of: 1.0\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:13<06:39, 13.76s/it]\n  7%|▋         | 2/30 [00:19<04:15,  9.13s/it]\n 10%|█         | 3/30 [00:26<03:37,  8.04s/it]\n 13%|█▎        | 4/30 [00:33<03:15,  7.53s/it]\n 17%|█▋        | 5/30 [00:39<03:01,  7.24s/it]\n 20%|██        | 6/30 [00:46<02:49,  7.07s/it]\n 23%|██▎       | 7/30 [00:53<02:40,  6.96s/it]\n 27%|██▋       | 8/30 [01:00<02:31,  6.89s/it]\n 30%|███       | 9/30 [01:06<02:23,  6.84s/it]\n 33%|███▎      | 10/30 [01:13<02:16,  6.81s/it]\n 37%|███▋      | 11/30 [01:20<02:09,  6.79s/it]\n 40%|████      | 12/30 [01:27<02:01,  6.78s/it]\n 43%|████▎     | 13/30 [01:33<01:54,  6.76s/it]\n 47%|████▋     | 14/30 [01:40<01:48,  6.76s/it]\n 50%|█████     | 15/30 [01:47<01:41,  6.75s/it]\n 53%|█████▎    | 16/30 [01:54<01:34,  6.75s/it]\n 57%|█████▋    | 17/30 [02:00<01:27,  6.75s/it]\n 60%|██████    | 18/30 [02:07<01:20,  6.75s/it]\n 63%|██████▎   | 19/30 [02:14<01:14,  6.74s/it]\n 67%|██████▋   | 20/30 [02:20<01:07,  6.74s/it]\n 70%|███████   | 21/30 [02:27<01:00,  6.74s/it]\n 73%|███████▎  | 22/30 [02:34<00:53,  6.74s/it]\n 77%|███████▋  | 23/30 [02:41<00:47,  6.73s/it]\n 80%|████████  | 24/30 [02:47<00:40,  6.73s/it]\n 83%|████████▎ | 25/30 [02:54<00:33,  6.73s/it]\n 87%|████████▋ | 26/30 [03:01<00:26,  6.73s/it]\n 90%|█████████ | 27/30 [03:08<00:20,  6.72s/it]\n 93%|█████████▎| 28/30 [03:14<00:13,  6.72s/it]\n 97%|█████████▋| 29/30 [03:21<00:06,  6.72s/it]\n100%|██████████| 30/30 [03:28<00:00,  6.72s/it]\n100%|██████████| 30/30 [03:28<00:00,  6.94s/it]",
  "metrics": {
    "predict_time": 233.443011344,
    "total_time": 287.333358
  },
  "output": "https://replicate.delivery/xezq/mFqnIdXCfkUuICKQVgs30lfBVFjSJyzueY93sPmXpxF4eCpPB/output.mp4",
  "started_at": "2024-12-12T21:43:14.883346Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-5bylcjibmjecy2on6c7xznf4migyjxznbstbn4fzd3d7d7lamkoq",
    "get": "https://api.replicate.com/v1/predictions/42wspzx285rmc0ckqk99tdda7w",
    "cancel": "https://api.replicate.com/v1/predictions/42wspzx285rmc0ckqk99tdda7w/cancel"
  },
  "version": "bad496d88086d5f60307291a512fdcb4fab0b30027e7ccbcc2ecf5e6606d5e20"
}

Generated in

3 minutes 53 seconds

Tweak it Share Report