prunaai/z-image 🔢📝❓ → 🖼️

▶️ 27.7K runs 📅 Jan 2026 ⚙️ Cog 0.16.9 ⚖️ License
text-to-image

About

An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Example Output

Prompt:

"A hyper-realistic, close-up portrait of a tribal elder from the Omo Valley, painted with intricate white chalk patterns and adorned with a headdress made of dried flowers, seed pods, and rusted bottle caps. The focus is razor-sharp on the texture of the skin, showing every pore, wrinkle, and scar that tells a story of survival. The background is a blurred, smoky hut interior, with the warm glow of a cooking fire reflecting in the subject's dark, soulful eyes. Shot on a Leica M6 with Kodak Portra 400 film grain aesthetic."

Output

Example output

Performance Metrics

11.26s Prediction Time
11.27s Total Time
All Input Parameters 
{
  "width": 1024,
  "height": 1024,
  "prompt": "A hyper-realistic, close-up portrait of a tribal elder from the Omo Valley, painted with intricate white chalk patterns and adorned with a headdress made of dried flowers, seed pods, and rusted bottle caps. The focus is razor-sharp on the texture of the skin, showing every pore, wrinkle, and scar that tells a story of survival. The background is a blurred, smoky hut interior, with the warm glow of a cooking fire reflecting in the subject's dark, soulful eyes. Shot on a Leica M6 with Kodak Portra 400 film grain aesthetic.",
  "output_format": "jpg",
  "guidance_scale": 3,
  "output_quality": 90,
  "negative_prompt": "",
  "num_inference_steps": 28
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
width Type: integerDefault: 1024Range: 64 - 2048
Width of the generated image
height Type: integerDefault: 1024Range: 64 - 2048
Height of the generated image
prompt (required) Type: string
Text prompt for image generation
output_format Default: jpg
Format of the output images
guidance_scale Type: numberDefault: 4Range: 0 - 20
Guidance scale for classifier-free guidance. Recommended range: 3.0-5.0
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
negative_prompt Type: stringDefault:
Negative prompt to specify what you don't want in the image
num_inference_steps Type: integerDefault: 28Range: 1 - 50
Number of inference steps. Recommended range: 28-50
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Using seed: 308608975
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:10,  2.52it/s]
  7%|▋         | 2/28 [00:00<00:08,  3.22it/s]
 11%|█         | 3/28 [00:01<00:08,  2.86it/s]
 14%|█▍        | 4/28 [00:01<00:08,  2.72it/s]
 18%|█▊        | 5/28 [00:01<00:08,  2.64it/s]
 21%|██▏       | 6/28 [00:02<00:08,  2.60it/s]
 25%|██▌       | 7/28 [00:02<00:08,  2.57it/s]
 29%|██▊       | 8/28 [00:03<00:07,  2.56it/s]
 32%|███▏      | 9/28 [00:03<00:07,  2.55it/s]
 36%|███▌      | 10/28 [00:03<00:07,  2.54it/s]
 39%|███▉      | 11/28 [00:04<00:06,  2.54it/s]
 43%|████▎     | 12/28 [00:04<00:06,  2.53it/s]
 46%|████▋     | 13/28 [00:05<00:05,  2.53it/s]
 50%|█████     | 14/28 [00:05<00:05,  2.53it/s]
 54%|█████▎    | 15/28 [00:05<00:05,  2.53it/s]
 57%|█████▋    | 16/28 [00:06<00:04,  2.53it/s]
 61%|██████    | 17/28 [00:06<00:04,  2.52it/s]
 64%|██████▍   | 18/28 [00:06<00:03,  2.53it/s]
 68%|██████▊   | 19/28 [00:07<00:03,  2.53it/s]
 71%|███████▏  | 20/28 [00:07<00:03,  2.53it/s]
 75%|███████▌  | 21/28 [00:08<00:02,  2.53it/s]
 79%|███████▊  | 22/28 [00:08<00:02,  2.53it/s]
 82%|████████▏ | 23/28 [00:08<00:01,  2.52it/s]
 86%|████████▌ | 24/28 [00:09<00:01,  2.53it/s]
 89%|████████▉ | 25/28 [00:09<00:01,  2.53it/s]
 93%|█████████▎| 26/28 [00:10<00:00,  2.53it/s]
 96%|█████████▋| 27/28 [00:10<00:00,  2.52it/s]
100%|██████████| 28/28 [00:10<00:00,  2.52it/s]
100%|██████████| 28/28 [00:10<00:00,  2.56it/s]
Version Details
Version ID
eb865cc448032613678cd0e4e99548671cdff1286bc04f0f605b3fc10fffe3aa
Version Created
January 27, 2026
Run on Replicate →