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

⭐ Official ▶️ 3.3M runs 📅 Nov 2024 ⚙️ Cog 0.15.8 🔗 GitHub ⚖️ License

fast-generation lora-inference text-to-image

About

The fastest image generation model tailored for fine-tuned use

Example Output

Prompt:

"a closeup BLKLGHT portrait photo of a cyberpunk"

Output

Performance Metrics

0.56s Prediction Time

0.57s Total Time

1 Images

All Input Parameters

{
  "prompt": "a closeup BLKLGHT portrait photo of a cyberpunk",
  "go_fast": true,
  "lora_scale": 0.8,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "lora_weights": "fofr/flux-black-light",
  "output_format": "webp",
  "output_quality": 80,
  "num_inference_steps": 4
}

Input Parameters

seed Type: integer: Random seed. Set for reproducible generation
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.
lora_scale Type: numberDefault: 1Range: -1 - 3: Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
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
lora_weights Type: string: Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
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
num_inference_steps Type: integerDefault: 4Range: 1 - 4: Number of denoising steps. 4 is recommended, 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

Lora fofr/flux-black-light already loaded
running quantized prediction
Using seed: 3844066928
  0%|          | 0/4 [00:00<?, ?it/s]
 50%|█████     | 2/4 [00:00<00:00, 18.98it/s]
100%|██████████| 4/4 [00:00<00:00, 13.74it/s]
100%|██████████| 4/4 [00:00<00:00, 14.32it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 83180e3ae073b7f87cd85b8bb649337412fd006d10db49e04ea5e821e87fbeb3
Version Created: June 24, 2025

Run on Replicate →