Prediction

5ez48nsghxrm40chfh1vrk080w

Status

Succeeded

Source

Web

Hardware

H100

Total duration

48.6s

Created

12 months ago

Input

model: dev
prompt: PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma
lora_scale: 1.1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 1.5
output_quality: 80
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
  "lora_scale": 1.1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 1.5,
  "output_quality": 80,
  "num_inference_steps": 28
}

npm install replicate

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 andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
  {
    input: {
      model: "dev",
      prompt: "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
      lora_scale: 1.1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 1.5,
      output_quality: 80,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

pip install replicate

Import the client:

import replicate

Run andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    input={
        "model": "dev",
        "prompt": "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
        "lora_scale": 1.1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 1.5,
        "output_quality": 80,
        "num_inference_steps": 28
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run andreasjansson/flux-goo 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": "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 1.5,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d \
  -i 'model="dev"' \
  -i 'prompt="PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma"' \
  -i 'lora_scale=1.1' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=1.5' \
  -i 'output_quality=80' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 1.5,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-08-22T22:45:12.472776Z",
  "created_at": "2024-08-22T22:44:23.823000Z",
  "data_removed": false,
  "error": null,
  "id": "5ez48nsghxrm40chfh1vrk080w",
  "input": {
    "model": "dev",
    "prompt": "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
    "lora_scale": 1.1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 1.5,
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 9540\nPrompt: PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma\ntxt2img mode\nUsing dev model\nLoading LoRA weights\nLoRA weights loaded successfully\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.53it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.96it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.74it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.65it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.61it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.58it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.56it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.55it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.54it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.54it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.53it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.53it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.53it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.53it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.52it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.52it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.53it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.53it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.52it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.52it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.53it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.53it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.52it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.52it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.52it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.53it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.52it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.52it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.55it/s]",
  "metrics": {
    "predict_time": 16.482869356,
    "total_time": 48.649776
  },
  "output": [
    "https://replicate.delivery/yhqm/5MgAeh8mS1QtK61oSezRfuWNfq76OVHef9KMj92mze7a8irqJA/out-0.webp"
  ],
  "started_at": "2024-08-22T22:44:55.989907Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/5ez48nsghxrm40chfh1vrk080w",
    "cancel": "https://api.replicate.com/v1/predictions/5ez48nsghxrm40chfh1vrk080w/cancel"
  },
  "version": "17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d"
}

Generated in

16.5 seconds

andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d

Prediction

Model

nm34mtbfwnrm60chfh4brs02k4

Status

Succeeded

Source

Web

Hardware

H100

Total duration

8.4s

Created

12 months ago

Input

model: dev
prompt: PLSM style, an image of a horse, made of yellow, red, and purple goo plasma
lora_scale: 1.1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 1.5
output_quality: 80
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "PLSM style, an image of a horse, made of yellow, red, and purple goo plasma",
  "lora_scale": 1.1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 1.5,
  "output_quality": 80,
  "num_inference_steps": 28
}

npm install replicate

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 andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
  {
    input: {
      model: "dev",
      prompt: "PLSM style, an image of a horse, made of yellow, red, and purple goo plasma",
      lora_scale: 1.1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 1.5,
      output_quality: 80,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

pip install replicate

Import the client:

import replicate

Run andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    input={
        "model": "dev",
        "prompt": "PLSM style, an image of a horse, made of yellow, red, and purple goo plasma",
        "lora_scale": 1.1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 1.5,
        "output_quality": 80,
        "num_inference_steps": 28
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run andreasjansson/flux-goo 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": "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a horse, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 1.5,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d \
  -i 'model="dev"' \
  -i 'prompt="PLSM style, an image of a horse, made of yellow, red, and purple goo plasma"' \
  -i 'lora_scale=1.1' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=1.5' \
  -i 'output_quality=80' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a horse, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 1.5,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-08-22T22:50:16.131130Z",
  "created_at": "2024-08-22T22:50:07.717000Z",
  "data_removed": false,
  "error": null,
  "id": "nm34mtbfwnrm60chfh4brs02k4",
  "input": {
    "model": "dev",
    "prompt": "PLSM style, an image of a horse, made of yellow, red, and purple goo plasma",
    "lora_scale": 1.1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 1.5,
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 8322\nPrompt: PLSM style, an image of a horse, made of yellow, red, and purple goo plasma\ntxt2img mode\nUsing dev model\nLoading LoRA weights\nweights already loaded!\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.51it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.94it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.75it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.67it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.62it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.59it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.57it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.56it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.56it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.56it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.55it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.55it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.55it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.55it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.54it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.55it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.54it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.54it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.55it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.55it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.55it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.55it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.55it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.54it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.54it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.54it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.54it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.54it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.56it/s]",
  "metrics": {
    "predict_time": 8.405517653,
    "total_time": 8.41413
  },
  "output": [
    "https://replicate.delivery/yhqm/d6uQfRL5bp0VUajl95IPnsL0bddQpelpyRitdGofI8LOVuqmA/out-0.webp"
  ],
  "started_at": "2024-08-22T22:50:07.725612Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nm34mtbfwnrm60chfh4brs02k4",
    "cancel": "https://api.replicate.com/v1/predictions/nm34mtbfwnrm60chfh4brs02k4/cancel"
  },
  "version": "17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d"
}

Generated in

8.4 seconds

andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d

Prediction

Model

qj58gza1z1rm20chfh5bxye9rw

Status

Succeeded

Source

Web

Hardware

H100

Total duration

17.3s

Created

12 months ago

Input

model: dev
prompt: PLSM style, an image of a dense forest, made of yellow, red, and purple goo plasma
lora_scale: 1.1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 1.5
output_quality: 80
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "PLSM style, an image of a dense forest, made of yellow, red, and purple goo plasma",
  "lora_scale": 1.1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 1.5,
  "output_quality": 80,
  "num_inference_steps": 28
}

npm install replicate

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 andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
  {
    input: {
      model: "dev",
      prompt: "PLSM style, an image of a dense forest, made of yellow, red, and purple goo plasma",
      lora_scale: 1.1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 1.5,
      output_quality: 80,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

pip install replicate

Import the client:

import replicate

Run andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    input={
        "model": "dev",
        "prompt": "PLSM style, an image of a dense forest, made of yellow, red, and purple goo plasma",
        "lora_scale": 1.1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 1.5,
        "output_quality": 80,
        "num_inference_steps": 28
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run andreasjansson/flux-goo 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": "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a dense forest, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 1.5,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d \
  -i 'model="dev"' \
  -i 'prompt="PLSM style, an image of a dense forest, made of yellow, red, and purple goo plasma"' \
  -i 'lora_scale=1.1' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=1.5' \
  -i 'output_quality=80' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a dense forest, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 1.5,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-08-22T22:52:24.275022Z",
  "created_at": "2024-08-22T22:52:07.032000Z",
  "data_removed": false,
  "error": null,
  "id": "qj58gza1z1rm20chfh5bxye9rw",
  "input": {
    "model": "dev",
    "prompt": "PLSM style, an image of a dense forest, made of yellow, red, and purple goo plasma",
    "lora_scale": 1.1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 1.5,
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 17439\nPrompt: PLSM style, an image of a dense forest, made of yellow, red, and purple goo plasma\ntxt2img mode\nUsing dev model\nLoading LoRA weights\nLoRA weights loaded successfully\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.50it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.93it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.74it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.66it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.61it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.58it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.56it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.56it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.54it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.54it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.54it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.54it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.53it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.53it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.53it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.53it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.53it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.52it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.53it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.53it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.53it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.52it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.53it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.53it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.52it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.52it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.53it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.53it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.55it/s]",
  "metrics": {
    "predict_time": 17.233267941,
    "total_time": 17.243022
  },
  "output": [
    "https://replicate.delivery/yhqm/jYBFyfOdTMwuN67Fb2KtjY14VB91x8ADNGgodiWkXIMUmrqJA/out-0.webp"
  ],
  "started_at": "2024-08-22T22:52:07.041754Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/qj58gza1z1rm20chfh5bxye9rw",
    "cancel": "https://api.replicate.com/v1/predictions/qj58gza1z1rm20chfh5bxye9rw/cancel"
  },
  "version": "17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d"
}

Generated in

17.2 seconds

andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d

Prediction

Model

nhy153pabsrm40chfh7a7592sr

Status

Succeeded

Source

Web

Hardware

H100

Total duration

24.0s

Created

12 months ago

Input

model: dev
prompt: PLSM style, an image of a city, made of yellow, red, and purple goo plasma
lora_scale: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 1.5
output_quality: 80
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "PLSM style, an image of a city, made of yellow, red, and purple goo plasma",
  "lora_scale": 1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 1.5,
  "output_quality": 80,
  "num_inference_steps": 28
}

npm install replicate

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 andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
  {
    input: {
      model: "dev",
      prompt: "PLSM style, an image of a city, made of yellow, red, and purple goo plasma",
      lora_scale: 1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 1.5,
      output_quality: 80,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

pip install replicate

Import the client:

import replicate

Run andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    input={
        "model": "dev",
        "prompt": "PLSM style, an image of a city, made of yellow, red, and purple goo plasma",
        "lora_scale": 1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 1.5,
        "output_quality": 80,
        "num_inference_steps": 28
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run andreasjansson/flux-goo 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": "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a city, made of yellow, red, and purple goo plasma",
      "lora_scale": 1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 1.5,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d \
  -i 'model="dev"' \
  -i 'prompt="PLSM style, an image of a city, made of yellow, red, and purple goo plasma"' \
  -i 'lora_scale=1' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=1.5' \
  -i 'output_quality=80' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a city, made of yellow, red, and purple goo plasma",
      "lora_scale": 1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 1.5,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-08-22T22:57:28.093581Z",
  "created_at": "2024-08-22T22:57:04.094000Z",
  "data_removed": false,
  "error": null,
  "id": "nhy153pabsrm40chfh7a7592sr",
  "input": {
    "model": "dev",
    "prompt": "PLSM style, an image of a city, made of yellow, red, and purple goo plasma",
    "lora_scale": 1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 1.5,
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 23795\nPrompt: PLSM style, an image of a city, made of yellow, red, and purple goo plasma\ntxt2img mode\nUsing dev model\nLoading LoRA weights\nLoRA weights loaded successfully\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.68it/s]\n  7%|▋         | 2/28 [00:00<00:06,  4.23it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.95it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.82it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.75it/s]\n 21%|██▏       | 6/28 [00:01<00:05,  3.73it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.71it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.69it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.68it/s]\n 36%|███▌      | 10/28 [00:02<00:04,  3.68it/s]\n 39%|███▉      | 11/28 [00:02<00:04,  3.67it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.67it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.66it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.66it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.66it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.66it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.66it/s]\n 64%|██████▍   | 18/28 [00:04<00:02,  3.66it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.66it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.66it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.66it/s]\n 79%|███████▊  | 22/28 [00:05<00:01,  3.66it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.66it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.65it/s]\n 89%|████████▉ | 25/28 [00:06<00:00,  3.65it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.65it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.65it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.65it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.69it/s]",
  "metrics": {
    "predict_time": 17.055186729,
    "total_time": 23.999581
  },
  "output": [
    "https://replicate.delivery/yhqm/UUrxGOdALfSvBqBYnbuROiExDGHFc0SQakOG95gdzGhrorqJA/out-0.webp"
  ],
  "started_at": "2024-08-22T22:57:11.038394Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nhy153pabsrm40chfh7a7592sr",
    "cancel": "https://api.replicate.com/v1/predictions/nhy153pabsrm40chfh7a7592sr/cancel"
  },
  "version": "17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d"
}

Generated in

17.1 seconds

andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d

Prediction

Model

mddwsgg5ehrm60chfh89nb123m

Status

Succeeded

Source

Web

Hardware

H100

Total duration

23.3s

Created

12 months ago

Input

model: dev
prompt: PLSM style, an image of a dramatic alien planet, made of yellow, red, and purple goo plasma
lora_scale: 1.1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 2
output_quality: 80
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "PLSM style, an image of a dramatic alien planet, made of yellow, red, and purple goo plasma",
  "lora_scale": 1.1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 2,
  "output_quality": 80,
  "num_inference_steps": 28
}

npm install replicate

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 andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
  {
    input: {
      model: "dev",
      prompt: "PLSM style, an image of a dramatic alien planet, made of yellow, red, and purple goo plasma",
      lora_scale: 1.1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 2,
      output_quality: 80,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

pip install replicate

Import the client:

import replicate

Run andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    input={
        "model": "dev",
        "prompt": "PLSM style, an image of a dramatic alien planet, made of yellow, red, and purple goo plasma",
        "lora_scale": 1.1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 2,
        "output_quality": 80,
        "num_inference_steps": 28
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run andreasjansson/flux-goo 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": "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a dramatic alien planet, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d \
  -i 'model="dev"' \
  -i 'prompt="PLSM style, an image of a dramatic alien planet, made of yellow, red, and purple goo plasma"' \
  -i 'lora_scale=1.1' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=2' \
  -i 'output_quality=80' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a dramatic alien planet, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-08-22T22:58:48.047104Z",
  "created_at": "2024-08-22T22:58:24.756000Z",
  "data_removed": false,
  "error": null,
  "id": "mddwsgg5ehrm60chfh89nb123m",
  "input": {
    "model": "dev",
    "prompt": "PLSM style, an image of a dramatic alien planet, made of yellow, red, and purple goo plasma",
    "lora_scale": 1.1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 2,
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 56148\nPrompt: PLSM style, an image of a dramatic alien planet, made of yellow, red, and purple goo plasma\ntxt2img mode\nUsing dev model\nLoading LoRA weights\nLoRA weights loaded successfully\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.51it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.95it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.75it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.66it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.61it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.58it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.56it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.55it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.54it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.54it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.54it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.53it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.53it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.53it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.53it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.53it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.52it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.53it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.54it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.53it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.53it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.53it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.54it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.53it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.53it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.54it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.54it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.54it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.55it/s]",
  "metrics": {
    "predict_time": 17.702627298,
    "total_time": 23.291104
  },
  "output": [
    "https://replicate.delivery/yhqm/oBrqShITcEaILZXUKEdC2n2sBhMsCRAM1fEHHeLf6Y8OluqmA/out-0.webp"
  ],
  "started_at": "2024-08-22T22:58:30.344477Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/mddwsgg5ehrm60chfh89nb123m",
    "cancel": "https://api.replicate.com/v1/predictions/mddwsgg5ehrm60chfh89nb123m/cancel"
  },
  "version": "17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d"
}

Generated in

17.7 seconds

andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d

Prediction

Model

gc83em4h9xrm20chfh8s692q5w

Status

Succeeded

Source

Web

Hardware

H100

Total duration

14.3s

Created

12 months ago

Input

model: dev
prompt: PLSM style, an image of a landscape on a dramatic alien planet, made of yellow, red, and purple goo plasma
lora_scale: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 1.5
output_quality: 80
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "PLSM style, an image of a landscape on a dramatic alien planet, made of yellow, red, and purple goo plasma",
  "lora_scale": 1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 1.5,
  "output_quality": 80,
  "num_inference_steps": 28
}

npm install replicate

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 andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
  {
    input: {
      model: "dev",
      prompt: "PLSM style, an image of a landscape on a dramatic alien planet, made of yellow, red, and purple goo plasma",
      lora_scale: 1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 1.5,
      output_quality: 80,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

pip install replicate

Import the client:

import replicate

Run andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    input={
        "model": "dev",
        "prompt": "PLSM style, an image of a landscape on a dramatic alien planet, made of yellow, red, and purple goo plasma",
        "lora_scale": 1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 1.5,
        "output_quality": 80,
        "num_inference_steps": 28
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run andreasjansson/flux-goo 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": "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a landscape on a dramatic alien planet, made of yellow, red, and purple goo plasma",
      "lora_scale": 1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 1.5,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d \
  -i 'model="dev"' \
  -i 'prompt="PLSM style, an image of a landscape on a dramatic alien planet, made of yellow, red, and purple goo plasma"' \
  -i 'lora_scale=1' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=1.5' \
  -i 'output_quality=80' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a landscape on a dramatic alien planet, made of yellow, red, and purple goo plasma",
      "lora_scale": 1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 1.5,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-08-22T23:00:20.368780Z",
  "created_at": "2024-08-22T23:00:06.095000Z",
  "data_removed": false,
  "error": null,
  "id": "gc83em4h9xrm20chfh8s692q5w",
  "input": {
    "model": "dev",
    "prompt": "PLSM style, an image of a landscape on a dramatic alien planet, made of yellow, red, and purple goo plasma",
    "lora_scale": 1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 1.5,
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 18405\nPrompt: PLSM style, an image of a landscape on a dramatic alien planet, made of yellow, red, and purple goo plasma\ntxt2img mode\nUsing dev model\nLoading LoRA weights\nweights already loaded!\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.66it/s]\n  7%|▋         | 2/28 [00:00<00:06,  4.21it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.93it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.81it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.75it/s]\n 21%|██▏       | 6/28 [00:01<00:05,  3.71it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.68it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.67it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.66it/s]\n 36%|███▌      | 10/28 [00:02<00:04,  3.65it/s]\n 39%|███▉      | 11/28 [00:02<00:04,  3.65it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.64it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.65it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.64it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.64it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.63it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.63it/s]\n 64%|██████▍   | 18/28 [00:04<00:02,  3.63it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.63it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.63it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.63it/s]\n 79%|███████▊  | 22/28 [00:05<00:01,  3.64it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.64it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.64it/s]\n 89%|████████▉ | 25/28 [00:06<00:00,  3.64it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.64it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.64it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.63it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.67it/s]",
  "metrics": {
    "predict_time": 8.212518616,
    "total_time": 14.27378
  },
  "output": [
    "https://replicate.delivery/yhqm/nToWCCi2B8pDNNkhZkgpV89RvGfIlRp7QaRJlkRfHroEUXVTA/out-0.webp"
  ],
  "started_at": "2024-08-22T23:00:12.156262Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/gc83em4h9xrm20chfh8s692q5w",
    "cancel": "https://api.replicate.com/v1/predictions/gc83em4h9xrm20chfh8s692q5w/cancel"
  },
  "version": "17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d"
}

Generated in

8.2 seconds

andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d

Prediction

Model

8fx62v3qqsrm40chfhabx5srhr

Status

Succeeded

Source

Web

Hardware

H100

Total duration

9.5s

Created

12 months ago

Input

model: dev
prompt: PLSM style, an image of a burning fire, made of yellow, red, and purple goo plasma
lora_scale: 1.1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 2
output_quality: 80
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "PLSM style, an image of a burning fire, made of yellow, red, and purple goo plasma",
  "lora_scale": 1.1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 2,
  "output_quality": 80,
  "num_inference_steps": 28
}

npm install replicate

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 andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
  {
    input: {
      model: "dev",
      prompt: "PLSM style, an image of a burning fire, made of yellow, red, and purple goo plasma",
      lora_scale: 1.1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 2,
      output_quality: 80,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

pip install replicate

Import the client:

import replicate

Run andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    input={
        "model": "dev",
        "prompt": "PLSM style, an image of a burning fire, made of yellow, red, and purple goo plasma",
        "lora_scale": 1.1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 2,
        "output_quality": 80,
        "num_inference_steps": 28
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run andreasjansson/flux-goo 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": "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a burning fire, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d \
  -i 'model="dev"' \
  -i 'prompt="PLSM style, an image of a burning fire, made of yellow, red, and purple goo plasma"' \
  -i 'lora_scale=1.1' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=2' \
  -i 'output_quality=80' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a burning fire, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-08-22T23:03:25.643679Z",
  "created_at": "2024-08-22T23:03:16.158000Z",
  "data_removed": false,
  "error": null,
  "id": "8fx62v3qqsrm40chfhabx5srhr",
  "input": {
    "model": "dev",
    "prompt": "PLSM style, an image of a burning fire, made of yellow, red, and purple goo plasma",
    "lora_scale": 1.1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 2,
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 29128\nPrompt: PLSM style, an image of a burning fire, made of yellow, red, and purple goo plasma\ntxt2img mode\nUsing dev model\nLoading LoRA weights\nweights already loaded!\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.52it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.96it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.76it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.67it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.63it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.60it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.58it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.57it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.56it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.56it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.56it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.55it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.55it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.55it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.55it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.55it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.55it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.55it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.55it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.55it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.55it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.55it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.55it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.55it/s]\n 89%|████████▉ | 25/28 [00:06<00:00,  3.55it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.55it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.55it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.55it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.57it/s]",
  "metrics": {
    "predict_time": 8.381131717,
    "total_time": 9.485679
  },
  "output": [
    "https://replicate.delivery/yhqm/OEC6gom5ORLoAN5WD2KFzp4NlIawHwE8IVx5jtJiexmeWXVTA/out-0.webp"
  ],
  "started_at": "2024-08-22T23:03:17.262548Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/8fx62v3qqsrm40chfhabx5srhr",
    "cancel": "https://api.replicate.com/v1/predictions/8fx62v3qqsrm40chfhabx5srhr/cancel"
  },
  "version": "17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d"
}

Generated in

8.4 seconds

andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d

Prediction

Model

79p04gze3nrm40chfhatysp1hg

Status

Succeeded

Source

Web

Hardware

H100

Total duration

8.4s

Created

12 months ago

Input

model: dev
prompt: PLSM style, an image of a rose, made of yellow, red, and purple goo plasma
lora_scale: 1.1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 2
output_quality: 80
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "PLSM style, an image of a rose, made of yellow, red, and purple goo plasma",
  "lora_scale": 1.1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 2,
  "output_quality": 80,
  "num_inference_steps": 28
}

npm install replicate

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 andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
  {
    input: {
      model: "dev",
      prompt: "PLSM style, an image of a rose, made of yellow, red, and purple goo plasma",
      lora_scale: 1.1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 2,
      output_quality: 80,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

pip install replicate

Import the client:

import replicate

Run andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    input={
        "model": "dev",
        "prompt": "PLSM style, an image of a rose, made of yellow, red, and purple goo plasma",
        "lora_scale": 1.1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 2,
        "output_quality": 80,
        "num_inference_steps": 28
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run andreasjansson/flux-goo 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": "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a rose, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d \
  -i 'model="dev"' \
  -i 'prompt="PLSM style, an image of a rose, made of yellow, red, and purple goo plasma"' \
  -i 'lora_scale=1.1' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=2' \
  -i 'output_quality=80' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a rose, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-08-22T23:05:00.391180Z",
  "created_at": "2024-08-22T23:04:51.997000Z",
  "data_removed": false,
  "error": null,
  "id": "79p04gze3nrm40chfhatysp1hg",
  "input": {
    "model": "dev",
    "prompt": "PLSM style, an image of a rose, made of yellow, red, and purple goo plasma",
    "lora_scale": 1.1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 2,
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 54953\nPrompt: PLSM style, an image of a rose, made of yellow, red, and purple goo plasma\ntxt2img mode\nUsing dev model\nLoading LoRA weights\nweights already loaded!\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.53it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.95it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.75it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.65it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.61it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.59it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.57it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.55it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.55it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.55it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.54it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.53it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.54it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.54it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.53it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.53it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.54it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.54it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.53it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.53it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.53it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.54it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.53it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.53it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.53it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.54it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.53it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.53it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.55it/s]",
  "metrics": {
    "predict_time": 8.385020539,
    "total_time": 8.39418
  },
  "output": [
    "https://replicate.delivery/yhqm/kTcJuzrs4uZWANQZCS2OVohTdnloDHyLyF4Gb22cKCDH2V1E/out-0.webp"
  ],
  "started_at": "2024-08-22T23:04:52.006160Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/79p04gze3nrm40chfhatysp1hg",
    "cancel": "https://api.replicate.com/v1/predictions/79p04gze3nrm40chfhatysp1hg/cancel"
  },
  "version": "17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d"
}

Generated in

8.4 seconds

andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d

Prediction

Model

18rkpnnezdrm60chfhe96ft7jc

Status

Succeeded

Source

Web

Hardware

H100

Total duration

17.9s

Created

12 months ago

Input

model: dev
prompt: PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma
lora_scale: 1.1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 2
output_quality: 80
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
  "lora_scale": 1.1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 2,
  "output_quality": 80,
  "num_inference_steps": 28
}

npm install replicate

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 andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
  {
    input: {
      model: "dev",
      prompt: "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
      lora_scale: 1.1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 2,
      output_quality: 80,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

pip install replicate

Import the client:

import replicate

Run andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    input={
        "model": "dev",
        "prompt": "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
        "lora_scale": 1.1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 2,
        "output_quality": 80,
        "num_inference_steps": 28
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run andreasjansson/flux-goo 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": "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d \
  -i 'model="dev"' \
  -i 'prompt="PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma"' \
  -i 'lora_scale=1.1' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=2' \
  -i 'output_quality=80' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-08-22T23:12:32.487591Z",
  "created_at": "2024-08-22T23:12:14.587000Z",
  "data_removed": false,
  "error": null,
  "id": "18rkpnnezdrm60chfhe96ft7jc",
  "input": {
    "model": "dev",
    "prompt": "PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma",
    "lora_scale": 1.1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 2,
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 39448\nPrompt: PLSM style, an image of a tiger, made of yellow, red, and purple goo plasma\ntxt2img mode\nUsing dev model\nLoading LoRA weights\nLoRA weights loaded successfully\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.52it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.96it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.76it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.66it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.62it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.59it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.57it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.56it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.56it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.55it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.55it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.55it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.55it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.55it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.55it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.55it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.54it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.54it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.54it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.54it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.54it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.54it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.54it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.54it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.54it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.54it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.54it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.54it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.56it/s]",
  "metrics": {
    "predict_time": 17.891634893,
    "total_time": 17.900591
  },
  "output": [
    "https://replicate.delivery/yhqm/QzEKxI7rqBKrO56xXbdSUJEMz6gLSpm23Ha6h6dVGdA43V1E/out-0.webp"
  ],
  "started_at": "2024-08-22T23:12:14.595956Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/18rkpnnezdrm60chfhe96ft7jc",
    "cancel": "https://api.replicate.com/v1/predictions/18rkpnnezdrm60chfhe96ft7jc/cancel"
  },
  "version": "17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d"
}

Generated in

17.9 seconds

andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d

Prediction

Model

pab8t5dtndrm20chfhbtd6br7r

Status

Succeeded

Source

Web

Hardware

H100

Total duration

34.1s

Created

12 months ago

Input

model: dev
prompt: PLSM style, an image of the word PLASMA, made of yellow, red, and purple goo plasma
lora_scale: 1.1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 2
output_quality: 80
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "PLSM style, an image of the word PLASMA, made of yellow, red, and purple goo plasma",
  "lora_scale": 1.1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 2,
  "output_quality": 80,
  "num_inference_steps": 28
}

npm install replicate

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 andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
  {
    input: {
      model: "dev",
      prompt: "PLSM style, an image of the word PLASMA, made of yellow, red, and purple goo plasma",
      lora_scale: 1.1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 2,
      output_quality: 80,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

pip install replicate

Import the client:

import replicate

Run andreasjansson/flux-goo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    input={
        "model": "dev",
        "prompt": "PLSM style, an image of the word PLASMA, made of yellow, red, and purple goo plasma",
        "lora_scale": 1.1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 2,
        "output_quality": 80,
        "num_inference_steps": 28
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run andreasjansson/flux-goo 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": "andreasjansson/flux-goo:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d",
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of the word PLASMA, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d \
  -i 'model="dev"' \
  -i 'prompt="PLSM style, an image of the word PLASMA, made of yellow, red, and purple goo plasma"' \
  -i 'lora_scale=1.1' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=2' \
  -i 'output_quality=80' \
  -i 'num_inference_steps=28'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/andreasjansson/flux-goo@sha256:17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "PLSM style, an image of the word PLASMA, made of yellow, red, and purple goo plasma",
      "lora_scale": 1.1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-08-22T23:07:24.003747Z",
  "created_at": "2024-08-22T23:06:49.899000Z",
  "data_removed": false,
  "error": null,
  "id": "pab8t5dtndrm20chfhbtd6br7r",
  "input": {
    "model": "dev",
    "prompt": "PLSM style, an image of the word PLASMA, made of yellow, red, and purple goo plasma",
    "lora_scale": 1.1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 2,
    "output_quality": 80,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 26991\nPrompt: PLSM style, an image of the word PLASMA, made of yellow, red, and purple goo plasma\ntxt2img mode\nUsing dev model\nLoading LoRA weights\nEnsuring enough disk space...\nFree disk space: 9549500669952\nDownloading weights\n2024-08-22T23:06:49Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/b4f70436c3e28e42 url=https://replicate.delivery/yhqm/MHJmIF7zlLKXPNN9LKN5yxYUuC7SyzKjMBtqeVwUGdPCpqqJA/trained_model.tar\n2024-08-22T23:06:51Z | INFO  | [ Complete ] dest=/src/weights-cache/b4f70436c3e28e42 size=\"172 MB\" total_elapsed=1.823s url=https://replicate.delivery/yhqm/MHJmIF7zlLKXPNN9LKN5yxYUuC7SyzKjMBtqeVwUGdPCpqqJA/trained_model.tar\nb''\nDownloaded weights in 1.8533737659454346 seconds\nLoRA weights loaded successfully\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.52it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.93it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.74it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.64it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.60it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.57it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.56it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.53it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.55it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.53it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.53it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.53it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.53it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.52it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.53it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.53it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.54it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.54it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.53it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.54it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.54it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.52it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.54it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.54it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.54it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.54it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.53it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.54it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.55it/s]",
  "metrics": {
    "predict_time": 34.102632688,
    "total_time": 34.104747
  },
  "output": [
    "https://replicate.delivery/yhqm/climqfC4LaSqfkxTfnUPfxi85OCE2uB3jlBw57CChtfeq2V1E/out-0.webp"
  ],
  "started_at": "2024-08-22T23:06:49.901114Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/pab8t5dtndrm20chfhbtd6br7r",
    "cancel": "https://api.replicate.com/v1/predictions/pab8t5dtndrm20chfhbtd6br7r/cancel"
  },
  "version": "17db11dcf58d8bddfb917583225aa438e00b47d3af2c245606a0fccc83f6eb3d"
}

Generated in

34.1 seconds