prunaai/hidream-e1.1 🔢🖼️📝❓✓ → 🖼️

▶️ 27.2K runs 📅 May 2025 ⚙️ Cog 0.14.7 🔗 GitHub ⚖️ License

cartoon-style fast-processing image-editing image-to-3d-animation webp-output

About

Edit an image with a prompt. This is the hidream-e1.1 model accelerated with the pruna optimisation engine.

Example Output

Prompt:

"Convert the image into a 3D animated style."

Output

Performance Metrics

14.74s Prediction Time

14.76s Total Time

All Input Parameters

{
  "seed": -1,
  "image": "https://raw.githubusercontent.com/HiDream-ai/HiDream-E1/refs/heads/main/assets/test_1.png",
  "prompt": "Convert the image into a 3D animated style.",
  "speed_mode": "Extra Juiced 🚀 (even more speed)",
  "clip_cfg_norm": true,
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "refine_strength": 0.3,
  "num_inference_steps": 28,
  "image_guidance_scale": 2
}

Input Parameters

seed Type: integerDefault: -1: Random seed (-1 for random)
image Type: string: Input image to edit.
prompt (required) Type: string: Prompt
speed_mode Default: Juiced 🔥 (more speed): Speed optimization level
clip_cfg_norm Type: booleanDefault: true: Whether to use CLIP CFG normalization
output_format Default: webp: Output format
guidance_scale Type: numberDefault: 2.5Range: 0 - 10: Guidance scale
output_quality Type: integerDefault: 100Range: 1 - 100: Output quality (for jpg and webp)
refine_strength Type: numberDefault: 0.3Range: 0 - 1: Strength of refinement
num_inference_steps Type: integerDefault: 28Range: 1 - 1000: Number of inference steps
image_guidance_scale Type: numberDefault: 1Range: 0 - 10: Image guidance scale

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Running inference...
  0%|          | 0/28 [00:00<?, ?it/s]
 54%|█████▎    | 15/28 [00:08<00:07,  1.85it/s]
100%|██████████| 28/28 [00:13<00:00,  2.02it/s]

Version Details

Version ID: 433436facdc1172b6efcb801eb6f345d7858a32200d24e5febaccfb4b44ad66f
Version Created: July 26, 2025

Run on Replicate →