chakify / flux-dev-lora-jambox

(Updated 5 months, 4 weeks ago)

Warm

Public
28 runs
H100

Iterate in playground

Run with an API

Playground API Examples README Versions

Prediction

chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9

Model

chakify/flux-dev-lora-jambox:9dfdeb3a

j6br99xp91rmc0ckvzyr157md0

Status

Succeeded

Source

Web

Hardware

H100

Total duration

9.3s

Created

6 months ago

Input

model: dev
prompt: Red JAMBOX on the coffee table
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "Red JAMBOX on the coffee table",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

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 chakify/flux-dev-lora-jambox using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9",
  {
    input: {
      model: "dev",
      prompt: "Red JAMBOX on the coffee table",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      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.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run chakify/flux-dev-lora-jambox using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9",
    input={
        "model": "dev",
        "prompt": "Red JAMBOX on the coffee table",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

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

Run chakify/flux-dev-lora-jambox 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": "chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9",
    "input": {
      "model": "dev",
      "prompt": "Red JAMBOX on the coffee table",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "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/chakify/flux-dev-lora-jambox@sha256:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9 \
  -i 'model="dev"' \
  -i 'prompt="Red JAMBOX on the coffee table"' \
  -i 'go_fast=false' \
  -i 'lora_scale=1' \
  -i 'megapixels="1"' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=3' \
  -i 'output_quality=80' \
  -i 'prompt_strength=0.8' \
  -i 'extra_lora_scale=1' \
  -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/chakify/flux-dev-lora-jambox@sha256:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "Red JAMBOX on the coffee table",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-12-19T17:36:16.023522Z",
  "created_at": "2024-12-19T17:36:06.728000Z",
  "data_removed": false,
  "error": null,
  "id": "j6br99xp91rmc0ckvzyr157md0",
  "input": {
    "model": "dev",
    "prompt": "Red JAMBOX on the coffee table",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2024-12-19 17:36:07.119 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2024-12-19 17:36:07.119 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  91%|█████████▏| 278/304 [00:00<00:00, 2761.17it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2703.83it/s]\n2024-12-19 17:36:07.232 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.11s\nfree=28937297399808\nDownloading weights\n2024-12-19T17:36:07Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpxfzw_6tw/weights url=https://replicate.delivery/xezq/d5bqeLHzgyTgB6ZNTgeRiQz2354rWndrtnnSaf9XszVNDB5nA/trained_model.tar\n2024-12-19T17:36:09Z | INFO  | [ Complete ] dest=/tmp/tmpxfzw_6tw/weights size=\"172 MB\" total_elapsed=2.383s url=https://replicate.delivery/xezq/d5bqeLHzgyTgB6ZNTgeRiQz2354rWndrtnnSaf9XszVNDB5nA/trained_model.tar\nDownloaded weights in 2.41s\n2024-12-19 17:36:09.642 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/31bce586c6a24140\n2024-12-19 17:36:09.713 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded\n2024-12-19 17:36:09.713 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2024-12-19 17:36:09.714 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  91%|█████████▏| 278/304 [00:00<00:00, 2762.72it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2705.08it/s]\n2024-12-19 17:36:09.826 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.18s\nUsing seed: 501\n0it [00:00, ?it/s]\n1it [00:00,  8.32it/s]\n2it [00:00,  5.78it/s]\n3it [00:00,  5.27it/s]\n4it [00:00,  5.06it/s]\n5it [00:00,  4.92it/s]\n6it [00:01,  4.82it/s]\n7it [00:01,  4.81it/s]\n8it [00:01,  4.80it/s]\n9it [00:01,  4.78it/s]\n10it [00:02,  4.74it/s]\n11it [00:02,  4.72it/s]\n12it [00:02,  4.73it/s]\n13it [00:02,  4.74it/s]\n14it [00:02,  4.74it/s]\n15it [00:03,  4.74it/s]\n16it [00:03,  4.72it/s]\n17it [00:03,  4.73it/s]\n18it [00:03,  4.73it/s]\n19it [00:03,  4.72it/s]\n20it [00:04,  4.73it/s]\n21it [00:04,  4.72it/s]\n22it [00:04,  4.72it/s]\n23it [00:04,  4.73it/s]\n24it [00:04,  4.73it/s]\n25it [00:05,  4.74it/s]\n26it [00:05,  4.73it/s]\n27it [00:05,  4.74it/s]\n28it [00:05,  4.74it/s]\n28it [00:05,  4.80it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 8.903158003,
    "total_time": 9.295522
  },
  "output": [
    "https://replicate.delivery/xezq/4EfJXA776URyYaefRU5NmPsc5KznSjs6YHJRoSCZL8UhcB5nA/out-0.webp"
  ],
  "started_at": "2024-12-19T17:36:07.120364Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-23m3itcumkdsit7llv2ldlzyvevxvt6avllma65fmzetr7awksba",
    "get": "https://api.replicate.com/v1/predictions/j6br99xp91rmc0ckvzyr157md0",
    "cancel": "https://api.replicate.com/v1/predictions/j6br99xp91rmc0ckvzyr157md0/cancel"
  },
  "version": "9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9"
}

Generated in

8.9 seconds

Tweak it ShareReport View full prediction

2024-12-19 17:36:07.119 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-19 17:36:07.119 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████▏| 278/304 [00:00<00:00, 2761.17it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2703.83it/s]
2024-12-19 17:36:07.232 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.11s
free=28937297399808
Downloading weights
2024-12-19T17:36:07Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpxfzw_6tw/weights url=https://replicate.delivery/xezq/d5bqeLHzgyTgB6ZNTgeRiQz2354rWndrtnnSaf9XszVNDB5nA/trained_model.tar
2024-12-19T17:36:09Z | INFO  | [ Complete ] dest=/tmp/tmpxfzw_6tw/weights size="172 MB" total_elapsed=2.383s url=https://replicate.delivery/xezq/d5bqeLHzgyTgB6ZNTgeRiQz2354rWndrtnnSaf9XszVNDB5nA/trained_model.tar
Downloaded weights in 2.41s
2024-12-19 17:36:09.642 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/31bce586c6a24140
2024-12-19 17:36:09.713 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2024-12-19 17:36:09.713 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-19 17:36:09.714 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████▏| 278/304 [00:00<00:00, 2762.72it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2705.08it/s]
2024-12-19 17:36:09.826 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.18s
Using seed: 501
0it [00:00, ?it/s]
1it [00:00,  8.32it/s]
2it [00:00,  5.78it/s]
3it [00:00,  5.27it/s]
4it [00:00,  5.06it/s]
5it [00:00,  4.92it/s]
6it [00:01,  4.82it/s]
7it [00:01,  4.81it/s]
8it [00:01,  4.80it/s]
9it [00:01,  4.78it/s]
10it [00:02,  4.74it/s]
11it [00:02,  4.72it/s]
12it [00:02,  4.73it/s]
13it [00:02,  4.74it/s]
14it [00:02,  4.74it/s]
15it [00:03,  4.74it/s]
16it [00:03,  4.72it/s]
17it [00:03,  4.73it/s]
18it [00:03,  4.73it/s]
19it [00:03,  4.72it/s]
20it [00:04,  4.73it/s]
21it [00:04,  4.72it/s]
22it [00:04,  4.72it/s]
23it [00:04,  4.73it/s]
24it [00:04,  4.73it/s]
25it [00:05,  4.74it/s]
26it [00:05,  4.73it/s]
27it [00:05,  4.74it/s]
28it [00:05,  4.74it/s]
28it [00:05,  4.80it/s]
Total safe images: 1 out of 1

Prediction

chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9

Model

chakify/flux-dev-lora-jambox:9dfdeb3a

c3m00t7myxrmc0ckw01tn99mh4

Status

Succeeded

Source

Web

Hardware

H100

Total duration

6.1s

Created

6 months ago

Input

model: dev
prompt: A family at the beach. Red JAMBOX in the middle of the beach towel.
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "A family at the beach. Red JAMBOX in the middle of the beach towel.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

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 chakify/flux-dev-lora-jambox using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9",
  {
    input: {
      model: "dev",
      prompt: "A family at the beach. Red JAMBOX in the middle of the beach towel.",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      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.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run chakify/flux-dev-lora-jambox using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9",
    input={
        "model": "dev",
        "prompt": "A family at the beach. Red JAMBOX in the middle of the beach towel.",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

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

Run chakify/flux-dev-lora-jambox 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": "chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9",
    "input": {
      "model": "dev",
      "prompt": "A family at the beach. Red JAMBOX in the middle of the beach towel.",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "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/chakify/flux-dev-lora-jambox@sha256:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9 \
  -i 'model="dev"' \
  -i 'prompt="A family at the beach. Red JAMBOX in the middle of the beach towel."' \
  -i 'go_fast=false' \
  -i 'lora_scale=1' \
  -i 'megapixels="1"' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=3' \
  -i 'output_quality=80' \
  -i 'prompt_strength=0.8' \
  -i 'extra_lora_scale=1' \
  -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/chakify/flux-dev-lora-jambox@sha256:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "A family at the beach. Red JAMBOX in the middle of the beach towel.",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-12-19T17:43:02.078764Z",
  "created_at": "2024-12-19T17:42:55.991000Z",
  "data_removed": false,
  "error": null,
  "id": "c3m00t7myxrmc0ckw01tn99mh4",
  "input": {
    "model": "dev",
    "prompt": "A family at the beach. Red JAMBOX in the middle of the beach towel.",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/d5bqeLHzgyTgB6ZNTgeRiQz2354rWndrtnnSaf9XszVNDB5nA/trained_model.tar already loaded\nUsing seed: 57833\n0it [00:00, ?it/s]\n1it [00:00,  8.37it/s]\n2it [00:00,  5.84it/s]\n3it [00:00,  5.33it/s]\n4it [00:00,  5.11it/s]\n5it [00:00,  4.98it/s]\n6it [00:01,  4.89it/s]\n7it [00:01,  4.86it/s]\n8it [00:01,  4.84it/s]\n9it [00:01,  4.83it/s]\n10it [00:01,  4.82it/s]\n11it [00:02,  4.79it/s]\n12it [00:02,  4.79it/s]\n13it [00:02,  4.80it/s]\n14it [00:02,  4.80it/s]\n15it [00:03,  4.78it/s]\n16it [00:03,  4.78it/s]\n17it [00:03,  4.79it/s]\n18it [00:03,  4.80it/s]\n19it [00:03,  4.80it/s]\n20it [00:04,  4.79it/s]\n21it [00:04,  4.78it/s]\n22it [00:04,  4.78it/s]\n23it [00:04,  4.78it/s]\n24it [00:04,  4.79it/s]\n25it [00:05,  4.79it/s]\n26it [00:05,  4.79it/s]\n27it [00:05,  4.78it/s]\n28it [00:05,  4.78it/s]\n28it [00:05,  4.86it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 6.079322364,
    "total_time": 6.087764
  },
  "output": [
    "https://replicate.delivery/xezq/b4I7O8bL7MKKFtZzRfLozt2kZuXYoDlqh5P1RNuvloSTaQeTA/out-0.webp"
  ],
  "started_at": "2024-12-19T17:42:55.999441Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-e27ui4cyc5e677yvfp6nxlau25u6dlrf7yqh73oqrxummtqjlqzq",
    "get": "https://api.replicate.com/v1/predictions/c3m00t7myxrmc0ckw01tn99mh4",
    "cancel": "https://api.replicate.com/v1/predictions/c3m00t7myxrmc0ckw01tn99mh4/cancel"
  },
  "version": "9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9"
}

Generated in

6.1 seconds

Tweak it ShareReport View full prediction

Prediction

chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9

Model

chakify/flux-dev-lora-jambox:9dfdeb3a

b27j1dy82nrm80ckw03vq0gcmc

Status

Succeeded

Source

Web

Hardware

H100

Total duration

8.7s

Created

6 months ago

Input

model: dev
prompt: Red JAMBOX in the middle of the bookselves, in an office with black bookshelves.
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "Red JAMBOX in the middle of the bookselves, in an office with black bookshelves.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

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 chakify/flux-dev-lora-jambox using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9",
  {
    input: {
      model: "dev",
      prompt: "Red JAMBOX in the middle of the bookselves, in an office with black bookshelves.",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      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.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run chakify/flux-dev-lora-jambox using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9",
    input={
        "model": "dev",
        "prompt": "Red JAMBOX in the middle of the bookselves, in an office with black bookshelves.",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

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

Run chakify/flux-dev-lora-jambox 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": "chakify/flux-dev-lora-jambox:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9",
    "input": {
      "model": "dev",
      "prompt": "Red JAMBOX in the middle of the bookselves, in an office with black bookshelves.",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "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/chakify/flux-dev-lora-jambox@sha256:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9 \
  -i 'model="dev"' \
  -i 'prompt="Red JAMBOX in the middle of the bookselves, in an office with black bookshelves."' \
  -i 'go_fast=false' \
  -i 'lora_scale=1' \
  -i 'megapixels="1"' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=3' \
  -i 'output_quality=80' \
  -i 'prompt_strength=0.8' \
  -i 'extra_lora_scale=1' \
  -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/chakify/flux-dev-lora-jambox@sha256:9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "dev",
      "prompt": "Red JAMBOX in the middle of the bookselves, in an office with black bookshelves.",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-12-19T17:47:15.338578Z",
  "created_at": "2024-12-19T17:47:06.645000Z",
  "data_removed": false,
  "error": null,
  "id": "b27j1dy82nrm80ckw03vq0gcmc",
  "input": {
    "model": "dev",
    "prompt": "Red JAMBOX in the middle of the bookselves, in an office with black bookshelves.",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2024-12-19 17:47:06.725 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2024-12-19 17:47:06.725 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  95%|█████████▌| 289/304 [00:00<00:00, 2887.86it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2785.06it/s]\n2024-12-19 17:47:06.835 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2024-12-19 17:47:06.835 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  55%|█████▌    | 168/304 [00:00<00:00, 1677.44it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 1751.35it/s]\n2024-12-19 17:47:07.009 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.28s\nfree=28661308735488\nDownloading weights\n2024-12-19T17:47:07Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpey9oot4v/weights url=https://replicate.delivery/xezq/d5bqeLHzgyTgB6ZNTgeRiQz2354rWndrtnnSaf9XszVNDB5nA/trained_model.tar\n2024-12-19T17:47:09Z | INFO  | [ Complete ] dest=/tmp/tmpey9oot4v/weights size=\"172 MB\" total_elapsed=2.013s url=https://replicate.delivery/xezq/d5bqeLHzgyTgB6ZNTgeRiQz2354rWndrtnnSaf9XszVNDB5nA/trained_model.tar\nDownloaded weights in 2.04s\n2024-12-19 17:47:09.050 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/31bce586c6a24140\n2024-12-19 17:47:09.123 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded\n2024-12-19 17:47:09.123 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2024-12-19 17:47:09.123 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  90%|████████▉ | 273/304 [00:00<00:00, 2725.71it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2658.18it/s]\n2024-12-19 17:47:09.238 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.19s\nUsing seed: 48234\n0it [00:00, ?it/s]\n1it [00:00,  8.35it/s]\n2it [00:00,  5.85it/s]\n3it [00:00,  5.33it/s]\n4it [00:00,  5.12it/s]\n5it [00:00,  5.01it/s]\n6it [00:01,  4.93it/s]\n7it [00:01,  4.89it/s]\n8it [00:01,  4.86it/s]\n9it [00:01,  4.85it/s]\n10it [00:01,  4.84it/s]\n11it [00:02,  4.83it/s]\n12it [00:02,  4.82it/s]\n13it [00:02,  4.82it/s]\n14it [00:02,  4.82it/s]\n15it [00:03,  4.81it/s]\n16it [00:03,  4.80it/s]\n17it [00:03,  4.81it/s]\n18it [00:03,  4.80it/s]\n19it [00:03,  4.80it/s]\n20it [00:04,  4.81it/s]\n21it [00:04,  4.81it/s]\n22it [00:04,  4.81it/s]\n23it [00:04,  4.81it/s]\n24it [00:04,  4.81it/s]\n25it [00:05,  4.81it/s]\n26it [00:05,  4.81it/s]\n27it [00:05,  4.81it/s]\n28it [00:05,  4.81it/s]\n28it [00:05,  4.88it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 8.612332211,
    "total_time": 8.693578
  },
  "output": [
    "https://replicate.delivery/xezq/f2mqe7esIoBlLpRRnfzeCua4Vp1wfPeUG4ln3JSAr0QpRcQeTA/out-0.webp"
  ],
  "started_at": "2024-12-19T17:47:06.726245Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-u7srefqh7whosvvzdy6yho3nsx5dhqqpnt6q3m4txluucb7v3fha",
    "get": "https://api.replicate.com/v1/predictions/b27j1dy82nrm80ckw03vq0gcmc",
    "cancel": "https://api.replicate.com/v1/predictions/b27j1dy82nrm80ckw03vq0gcmc/cancel"
  },
  "version": "9dfdeb3a61e1f7f2e056da4fbc9d3ebe7af637c17c0f06acfbfdcd3dec5be9e9"
}

Generated in

8.6 seconds

Tweak it ShareReport View full prediction

2024-12-19 17:47:06.725 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-19 17:47:06.725 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  95%|█████████▌| 289/304 [00:00<00:00, 2887.86it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2785.06it/s]
2024-12-19 17:47:06.835 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-19 17:47:06.835 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  55%|█████▌    | 168/304 [00:00<00:00, 1677.44it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 1751.35it/s]
2024-12-19 17:47:07.009 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.28s
free=28661308735488
Downloading weights
2024-12-19T17:47:07Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpey9oot4v/weights url=https://replicate.delivery/xezq/d5bqeLHzgyTgB6ZNTgeRiQz2354rWndrtnnSaf9XszVNDB5nA/trained_model.tar
2024-12-19T17:47:09Z | INFO  | [ Complete ] dest=/tmp/tmpey9oot4v/weights size="172 MB" total_elapsed=2.013s url=https://replicate.delivery/xezq/d5bqeLHzgyTgB6ZNTgeRiQz2354rWndrtnnSaf9XszVNDB5nA/trained_model.tar
Downloaded weights in 2.04s
2024-12-19 17:47:09.050 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/31bce586c6a24140
2024-12-19 17:47:09.123 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2024-12-19 17:47:09.123 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-19 17:47:09.123 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  90%|████████▉ | 273/304 [00:00<00:00, 2725.71it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2658.18it/s]
2024-12-19 17:47:09.238 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.19s
Using seed: 48234
0it [00:00, ?it/s]
1it [00:00,  8.35it/s]
2it [00:00,  5.85it/s]
3it [00:00,  5.33it/s]
4it [00:00,  5.12it/s]
5it [00:00,  5.01it/s]
6it [00:01,  4.93it/s]
7it [00:01,  4.89it/s]
8it [00:01,  4.86it/s]
9it [00:01,  4.85it/s]
10it [00:01,  4.84it/s]
11it [00:02,  4.83it/s]
12it [00:02,  4.82it/s]
13it [00:02,  4.82it/s]
14it [00:02,  4.82it/s]
15it [00:03,  4.81it/s]
16it [00:03,  4.80it/s]
17it [00:03,  4.81it/s]
18it [00:03,  4.80it/s]
19it [00:03,  4.80it/s]
20it [00:04,  4.81it/s]
21it [00:04,  4.81it/s]
22it [00:04,  4.81it/s]
23it [00:04,  4.81it/s]
24it [00:04,  4.81it/s]
25it [00:05,  4.81it/s]
26it [00:05,  4.81it/s]
27it [00:05,  4.81it/s]
28it [00:05,  4.81it/s]
28it [00:05,  4.88it/s]
Total safe images: 1 out of 1

Want to make some of these yourself?

Run this model