reve/remix 📝❓🖼️ → 🖼️

⭐ Official ▶️ 1.7K runs 📅 Oct 2025 ⚙️ Cog 0.16.8
image-compositing image-editing image-to-image text-to-image

About

Image generation model from Reve which handles multiple input reference images

Example Output

Prompt:

"Make him hold the purse"

Output

Example output

Performance Metrics

24.48s Prediction Time
24.49s Total Time
All Input Parameters 
{
  "prompt": "Make him hold the purse",
  "version": "latest",
  "aspect_ratio": "3:2",
  "reference_images": [
    "https://replicate.delivery/pbxt/NtxAZ0AmyDK0HXuElLlp2UDZnzFlkbTwjOl8af4eqR7BLCD6/03071b3fb9a138be7d9407bf4f9a2f076a14f501-yzHyahJT.webp",
    "https://replicate.delivery/pbxt/NtxAZ02QUbWiYKr8zRKs0thSiPc2x9lk8MbvC2FpVdfFlKYX/61acfa2e7283b39c8119400f07360f2c33bc6277-BQ6KI5U5.webp"
  ]
}
Input Parameters
prompt Type: stringDefault: A serene mountain landscape at sunset with snow-capped peaks
Text prompt for image generation
version Default: latest
The specific model version to use when generating the image
aspect_ratio Default: 3:2
The desired aspect ratio of the generated image
reference_images Type: array
List of 1-4 image files to remix from (Paths)
Output Schema

Output

Type: string • Format: uri

Version Details
Version ID
1db0ca2a3b7e1bf8628ab1b48a5b3652a55a4e4a486b6f235d6a238051a42863
Version Created
October 17, 2025
Run on Replicate →