black-forest-labs/flux-dev 🔢🖼️📝✓❓ → 🖼️

⭐ Official ▶️ 37.4M runs 📅 Jul 2024 ⚙️ Cog 0.15.8 🔗 GitHub ⚖️ License
image-to-image text-to-image

About

A 12 billion parameter rectified flow transformer capable of generating images from text descriptions

Example Output

Prompt:

"black forest gateau cake spelling out the words "FLUX DEV", tasty, food photography, dynamic shot"

Output

Example output

Performance Metrics

1.79s Prediction Time
1.79s Total Time
1 Images
All Input Parameters 
{
  "prompt": "black forest gateau cake spelling out the words \"FLUX DEV\", tasty, food photography, dynamic shot",
  "go_fast": true,
  "guidance": 3.5,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "output_quality": 80,
  "prompt_strength": 0.8,
  "num_inference_steps": 28
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
image Type: string
Input image for image to image mode. The aspect ratio of your output will match this image
prompt (required) Type: string
Prompt for generated image
go_fast Type: booleanDefault: true
Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16. Note that outputs will not be deterministic when this is enabled, even if you set a seed.
guidance Type: numberDefault: 3Range: 0 - 10
Guidance for generated image
megapixels Default: 1
Approximate number of megapixels for generated image
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of outputs to generate
aspect_ratio Default: 1:1
Aspect ratio for the generated image
output_format Default: webp
Format of the output images
output_quality Type: integerDefault: 80Range: 0 - 100
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
prompt_strength Type: numberDefault: 0.8Range: 0 - 1
Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
num_inference_steps Type: integerDefault: 28Range: 1 - 50
Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images.
Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs 
Using seed: 29936
Using seed: 29936
Generating 1 images...
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 15.06it/s]
 14%|█▍        | 4/28 [00:00<00:02, 11.31it/s]
 21%|██▏       | 6/28 [00:00<00:01, 13.78it/s]
 29%|██▊       | 8/28 [00:00<00:01, 15.39it/s]
 39%|███▉      | 11/28 [00:00<00:00, 19.25it/s]
 50%|█████     | 14/28 [00:00<00:00, 21.82it/s]
 64%|██████▍   | 18/28 [00:00<00:00, 25.81it/s]
 75%|███████▌  | 21/28 [00:01<00:00, 25.91it/s]
 86%|████████▌ | 24/28 [00:01<00:00, 21.91it/s]
 96%|█████████▋| 27/28 [00:01<00:00, 17.79it/s]
100%|██████████| 28/28 [00:01<00:00, 18.26it/s]
Generation took 1.691025972366333 seconds
Image generation took 1.69 seconds
Total safe images: 1 out of 1
Running safety checker took 0.02 seconds
Version Details
Version ID
6e4a938f85952bdabcc15aa329178c4d681c52bf25a0342403287dc26944661d
Version Created
June 25, 2025
Run on Replicate →