tencent/hunyuan-image-3 🔢📝✓❓ → 🖼️

⭐ Official ▶️ 42.3K runs 📅 Oct 2025 ⚙️ Cog 0.16.7 🔗 GitHub 📄 Paper ⚖️ License
text-to-image

About

A powerful native multimodal model for image generation (PrunaAI squeezed)

Example Output

Prompt:

"An illustration of a pink and brown butterfly on a pink background, with the black text “Hunyuan Image 3 on Replicate” below"

Output

Example output

Performance Metrics

27.60s Prediction Time
27.61s Total Time
All Input Parameters 
{
  "prompt": "An illustration of a pink and brown butterfly on a pink background, with the black text “Hunyuan Image 3 on Replicate” below",
  "go_fast": true,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "output_quality": 95
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
prompt (required) Type: string
Text prompt for image generation
go_fast Type: booleanDefault: true
Run faster predictions with additional optimizations.
aspect_ratio Default: 1:1
Aspect ratio for the generated image
output_format Default: webp
Format of the output images
output_quality Type: integerDefault: 95Range: 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
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: 192101
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:01<01:12,  1.47s/it]
  4%|▍         | 2/50 [00:02<01:06,  1.39s/it]
  6%|▌         | 3/50 [00:04<01:04,  1.37s/it]
  8%|▊         | 4/50 [00:05<01:02,  1.36s/it]
 14%|█▍        | 7/50 [00:06<00:33,  1.27it/s]
 20%|██        | 10/50 [00:08<00:25,  1.60it/s]
 26%|██▌       | 13/50 [00:09<00:20,  1.81it/s]
 32%|███▏      | 16/50 [00:10<00:17,  1.95it/s]
 38%|███▊      | 19/50 [00:12<00:15,  2.04it/s]
 44%|████▍     | 22/50 [00:13<00:13,  2.10it/s]
 50%|█████     | 25/50 [00:14<00:11,  2.14it/s]
 56%|█████▌    | 28/50 [00:16<00:10,  2.17it/s]
 62%|██████▏   | 31/50 [00:17<00:08,  2.19it/s]
 68%|██████▊   | 34/50 [00:18<00:07,  2.20it/s]
 74%|███████▍  | 37/50 [00:20<00:05,  2.21it/s]
 80%|████████  | 40/50 [00:21<00:04,  2.22it/s]
 86%|████████▌ | 43/50 [00:22<00:03,  2.23it/s]
 92%|█████████▏| 46/50 [00:24<00:01,  2.24it/s]
 98%|█████████▊| 49/50 [00:25<00:00,  2.24it/s]
100%|██████████| 50/50 [00:26<00:00,  1.79it/s]
100%|██████████| 50/50 [00:26<00:00,  1.86it/s]
Generation took 27.48 seconds
Total safe images: 1 out of 1
Version Details
Version ID
080dbbefcd1504ca5aeebaa2815fd51467d5bb793d2b1fb4eb4eb32ac22a3377
Version Created
October 7, 2025
Run on Replicate →