prunaai/ernie-image 🔢📝✓❓ → 🖼️

▶️ 445 runs 📅 Apr 2026 ⚙️ Cog 0.17.2 ⚖️ License
text-rendering text-to-image

About

ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu

Example Output

Prompt:

"a beautiful landscape"

Output

Example output

Performance Metrics

34.58s Prediction Time
34.59s Total Time
All Input Parameters 
{
  "width": 1024,
  "height": 1024,
  "prompt": "a beautiful landscape",
  "use_pe": true,
  "num_outputs": 1,
  "output_format": "jpg",
  "guidance_scale": 4,
  "output_quality": 80,
  "num_inference_steps": 50
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation.
width Type: integerDefault: 1024Range: 64 - 2048
Width of the generated image. Best results come from the model-card recommended sizes.
height Type: integerDefault: 1024Range: 64 - 2048
Height of the generated image. Best results come from the model-card recommended sizes.
prompt (required) Type: string
Text prompt for image generation
use_pe Type: booleanDefault: true
Enable the prompt enhancer recommended by the model card.
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of output images to generate.
output_format Default: jpg
Format of the output image.
guidance_scale Type: numberDefault: 4Range: 0 - 20
Classifier-free guidance scale.
output_quality Type: integerDefault: 80Range: 0 - 100
Quality when saving the output image, from 0 to 100.
num_inference_steps Type: integerDefault: 50Range: 1 - 100
Number of inference steps.
Output Schema

Output

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

Example Execution Logs 
Using seed: 719672883

  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:27,  1.77it/s]
  4%|▍         | 2/50 [00:00<00:21,  2.21it/s]
  6%|▌         | 3/50 [00:01<00:23,  2.00it/s]
  8%|▊         | 4/50 [00:02<00:24,  1.91it/s]
 10%|█         | 5/50 [00:02<00:24,  1.86it/s]
 12%|█▏        | 6/50 [00:03<00:23,  1.84it/s]
 14%|█▍        | 7/50 [00:03<00:23,  1.82it/s]
 16%|█▌        | 8/50 [00:04<00:23,  1.81it/s]
 18%|█▊        | 9/50 [00:04<00:22,  1.80it/s]
 20%|██        | 10/50 [00:05<00:22,  1.80it/s]
 22%|██▏       | 11/50 [00:05<00:21,  1.80it/s]
 24%|██▍       | 12/50 [00:06<00:21,  1.80it/s]
 26%|██▌       | 13/50 [00:07<00:20,  1.79it/s]
 28%|██▊       | 14/50 [00:07<00:20,  1.80it/s]
 30%|███       | 15/50 [00:08<00:19,  1.79it/s]
 32%|███▏      | 16/50 [00:08<00:18,  1.79it/s]
 34%|███▍      | 17/50 [00:09<00:18,  1.79it/s]
 36%|███▌      | 18/50 [00:09<00:17,  1.79it/s]
 38%|███▊      | 19/50 [00:10<00:17,  1.79it/s]
 40%|████      | 20/50 [00:10<00:16,  1.79it/s]
 42%|████▏     | 21/50 [00:11<00:16,  1.79it/s]
 44%|████▍     | 22/50 [00:12<00:15,  1.79it/s]
 46%|████▌     | 23/50 [00:12<00:15,  1.79it/s]
 48%|████▊     | 24/50 [00:13<00:14,  1.79it/s]
 50%|█████     | 25/50 [00:13<00:13,  1.79it/s]
 52%|█████▏    | 26/50 [00:14<00:13,  1.79it/s]
 54%|█████▍    | 27/50 [00:14<00:12,  1.79it/s]
 56%|█████▌    | 28/50 [00:15<00:12,  1.79it/s]
 58%|█████▊    | 29/50 [00:16<00:11,  1.79it/s]
 60%|██████    | 30/50 [00:16<00:11,  1.79it/s]
 62%|██████▏   | 31/50 [00:17<00:10,  1.79it/s]
 64%|██████▍   | 32/50 [00:17<00:10,  1.79it/s]
 66%|██████▌   | 33/50 [00:18<00:09,  1.79it/s]
 68%|██████▊   | 34/50 [00:18<00:08,  1.79it/s]
 70%|███████   | 35/50 [00:19<00:08,  1.79it/s]
 72%|███████▏  | 36/50 [00:19<00:07,  1.79it/s]
 74%|███████▍  | 37/50 [00:20<00:07,  1.79it/s]
 76%|███████▌  | 38/50 [00:21<00:06,  1.79it/s]
 78%|███████▊  | 39/50 [00:21<00:06,  1.79it/s]
 80%|████████  | 40/50 [00:22<00:05,  1.79it/s]
 82%|████████▏ | 41/50 [00:22<00:05,  1.79it/s]
 84%|████████▍ | 42/50 [00:23<00:04,  1.79it/s]
 86%|████████▌ | 43/50 [00:23<00:03,  1.79it/s]
 88%|████████▊ | 44/50 [00:24<00:03,  1.79it/s]
 90%|█████████ | 45/50 [00:24<00:02,  1.79it/s]
 92%|█████████▏| 46/50 [00:25<00:02,  1.79it/s]
 94%|█████████▍| 47/50 [00:26<00:01,  1.79it/s]
 96%|█████████▌| 48/50 [00:26<00:01,  1.79it/s]
 98%|█████████▊| 49/50 [00:27<00:00,  1.79it/s]
100%|██████████| 50/50 [00:27<00:00,  1.79it/s]
100%|██████████| 50/50 [00:27<00:00,  1.80it/s]
Version Details
Version ID
d5bfa4984edc317383025be5fd59a6a2d2b1992cf98bdddd788e5d5fa12a3ba4
Version Created
April 14, 2026
Run on Replicate →