ideogram-ai/ideogram-v3-balanced 🖼️🔢📝❓ → 🖼️

⭐ Official ▶️ 279.5K runs 📅 Apr 2025 ⚙️ Cog 0.16.7 📄 Paper ⚖️ License

image-inpainting image-style-transfer text-to-image

About

Balance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles

Example Output

Prompt:

"The text "V3 Balanced" in the center middle. A color film-inspired portrait of a young man and a young woman looking at each other, a shallow depth of field that blurs the surrounding elements, drawing attention to their eyes. The fine grain and cast suggest a high ISO film stock, while the wide aperture lens creates a pleasing bokeh effect, enhancing the candid and natural documentary style."

Output

Performance Metrics

8.31s Prediction Time

8.33s Total Time

1 Images

All Input Parameters

{
  "prompt": "The text \"V3 Balanced\" in the center middle. A color film-inspired portrait of a young man and a young woman looking at each other, a shallow depth of field that blurs the surrounding elements, drawing attention to their eyes. The fine grain and cast suggest a high ISO film stock, while the wide aperture lens creates a pleasing bokeh effect, enhancing the candid and natural documentary style.",
  "resolution": "None",
  "style_type": "None",
  "aspect_ratio": "3:2",
  "magic_prompt_option": "Auto"
}

Input Parameters

mask Type: string: A black and white image. Black pixels are inpainted, white pixels are preserved. The mask will be resized to match the image size.
seed Type: integerRange: ∞ - 2147483647: Random seed. Set for reproducible generation
image Type: string: An image file to use for inpainting. You must also use a mask.
prompt (required) Type: string: Text prompt for image generation
resolution Default: None: Resolution. Overrides aspect ratio. Ignored if an inpainting image is given.
style_type Default: None: The styles help define the specific aesthetic of the image you want to generate.
aspect_ratio Default: 1:1: Aspect ratio. Ignored if a resolution or inpainting image is given.
style_preset Default: None: Apply a predefined artistic style to the generated image (V3 models only).
magic_prompt_option Default: Auto: Magic Prompt will interpret your prompt and optimize it to maximize variety and quality of the images generated. You can also use it to write prompts in different languages.
style_reference_images Type: array: A list of images to use as style references.

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Using seed: 396639763
Moderating content...
Moderation complete in 0.19sec
Generating...
Prompt used: The text "V3 Balanced" in the center middle. A color film-inspired portrait of a young man and a young woman looking at each other, a shallow depth of field that blurs the surrounding elements, drawing attention to their eyes. The fine grain and cast suggest a high ISO film stock, while the wide aperture lens creates a pleasing bokeh effect, enhancing the candid and natural documentary style.
Image generation took 7.40 seconds
Downloading 1470627 bytes
Downloaded 1.40MB in 0.71sec

Version Details

Version ID: 7f00c6f29324fb51a748bb7dafc205456f850d7320e54db3ae78a2cbded4ab20
Version Created: September 30, 2025

Run on Replicate →