bytedance/hyper-flux-8step 🔢📝❓✓ → 🖼️

▶️ 17.7M runs 📅 Aug 2024 ⚙️ Cog 0.14.1 🔗 GitHub 📄 Paper ⚖️ License

flux hyper-sd text-to-image

About

Hyper FLUX 8-step by ByteDance

Example Output

Prompt:

"a dog smiling and looking directly at the camera, wearing a white t-shirt with the word "HYPER" printed on it."

Output

Performance Metrics

2.10s Prediction Time

4.42s Total Time

All Input Parameters

{
  "prompt": "a dog smiling and looking directly at the camera, wearing a white t-shirt with the word \"HYPER\" printed on it.",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "num_inference_steps": 8
}

Input Parameters

seed Type: integerDefault: 0: Random seed. Set for reproducible generation
width Type: integerDefault: 848Range: 256 - 1440: Width of the generated image. Optional, only used when aspect_ratio=custom. Must be a multiple of 16 (if it's not, it will be rounded to nearest multiple of 16)
height Type: integerDefault: 848Range: 256 - 1440: Height of the generated image. Optional, only used when aspect_ratio=custom. Must be a multiple of 16 (if it's not, it will be rounded to nearest multiple of 16)
prompt (required) Type: string: Prompt for generated image
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of images to output.
aspect_ratio Default: 1:1: Aspect ratio for the generated image. The size will always be 1 megapixel, i.e. 1024x1024 if aspect ratio is 1:1. To use arbitrary width and height, set aspect ratio to 'custom'.
output_format Default: webp: Format of the output images
guidance_scale Type: numberDefault: 3.5Range: 0 - 10: Guidance scale for the diffusion process
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: 8Range: 1 - 30: Number of inference steps
disable_safety_checker Type: booleanDefault: false: Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)

Output Schema

Output

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

Example Execution Logs

Using seed: 63685
Prompt: a dog smiling and looking directly at the camera, wearing a white t-shirt with the word "HYPER" printed on it.
txt2img mode
  0%|          | 0/8 [00:00<?, ?it/s]
 12%|█▎        | 1/8 [00:00<00:01,  4.34it/s]
 25%|██▌       | 2/8 [00:00<00:01,  5.51it/s]
 38%|███▊      | 3/8 [00:00<00:01,  4.91it/s]
 50%|█████     | 4/8 [00:00<00:00,  4.67it/s]
 62%|██████▎   | 5/8 [00:01<00:00,  4.55it/s]
 75%|███████▌  | 6/8 [00:01<00:00,  4.46it/s]
 88%|████████▊ | 7/8 [00:01<00:00,  4.43it/s]
100%|██████████| 8/8 [00:01<00:00,  4.40it/s]
100%|██████████| 8/8 [00:01<00:00,  4.55it/s]

Version Details

Version ID: 16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143
Version Created: March 18, 2025

Run on Replicate →