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

⭐ Official ▶️ 10.8K runs 📅 Jun 2025 ⚙️ Cog 0.16.8 ⚖️ License

image-to-image text-to-image

About

Inference model for FLUX.1 [pro] using custom `finetune_id`

Example Output

Prompt:

"A formula one CYBERCAB car"

Output

Performance Metrics

15.44s Prediction Time

15.46s Total Time

1 Images

All Input Parameters

{
  "steps": 40,
  "prompt": "A formula one CYBERCAB car",
  "guidance": 3,
  "finetune_id": "fc14d7bf-95bd-4dde-92c1-2dd7317721f6",
  "aspect_ratio": "3:2",
  "output_format": "jpg",
  "safety_tolerance": 2,
  "finetune_strength": 1,
  "prompt_upsampling": false
}

Input Parameters

seed Type: integer: Random seed. Set for reproducible generation
steps Type: integerDefault: 40Range: 1 - 50: Number of diffusion steps
width Type: integerRange: 256 - 1440: Width of the generated image in text-to-image mode. Only used when aspect_ratio=custom. Must be a multiple of 32 (if it's not, it will be rounded to nearest multiple of 32). Note: Ignored in img2img and inpainting modes.
height Type: integerRange: 256 - 1440: Height of the generated image in text-to-image mode. Only used when aspect_ratio=custom. Must be a multiple of 32 (if it's not, it will be rounded to nearest multiple of 32). Note: Ignored in img2img and inpainting modes.
prompt (required) Type: string: Text prompt for image generation
guidance Type: numberDefault: 3Range: 2 - 5: Controls the balance between adherence to the text prompt and image quality/diversity. Higher values make the output more closely match the prompt but may reduce overall image quality. Lower values allow for more creative freedom but might produce results less relevant to the prompt.
finetune_id (required) Type: string: Finetune ID for making images using a previously trained fine-tune. Only IDs from trainings made using Replicate's Flux Pro fine-tuning model are supported.
aspect_ratio Default: 1:1: Aspect ratio for the generated image
image_prompt Type: string: Image to use with Flux Redux. This is used together with the text prompt to guide the generation towards the composition of the image_prompt. Must be jpeg, png, gif, or webp.
output_format Default: jpg: Format of the output images.
safety_tolerance Type: integerDefault: 2Range: 1 - 6: Safety tolerance, 1 is most strict and 6 is most permissive
finetune_strength Type: numberDefault: 1Range: 0 - 2: Controls finetune influence
prompt_upsampling Type: booleanDefault: false: Automatically modify the prompt for more creative generation

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Running prediction... 

================ Training Details ================
Trigger Word: CYBERCAB

Other Details:
  Learning Rate: 1e-05
  Iterations: 100
  LoRA Rank: 32
  Mode: general
  Priority: quality
  Finetune Type: full
  Trained: 2025-01-17_13-48-43
==================================================
Using seed: 17313
Generating image...
Generated image in 14.9sec
Downloaded image in 0.32sec

Version Details

Version ID: 0515c6ddb21c9de66774a3b14be551de7030e4c1d06d5ca1c7f6038420647028
Version Created: November 10, 2025

Run on Replicate →