Browse all Higgsfield image models

Higgsfield Soul Image-to-Image

higgsfield/soul/image-to-image

Higgsfield Soul Image-to-Image

higgsfield/soul/image-to-image

Higgsfield Soul transforms a reference image into a stylized, realistic scene while preserving character identity. Choose from medium or high quality, a wide range of creative presets, and adjustable style strength.

Added Jul 31, 2026

Approx. Price

$0.090 per image

Model Type

image-to-image

Settings

Generation controls available for this model.

Images Per Run

Up to 1

Output images

Input Images

Up to 1

Reference/edit images accepted • Route max 30 MB

Output Sizes

Square
Portrait
Landscape
up to 2,048px

Number of Images

Default

1

Quality

Select

Default

medium

Options (2)

Medium, High

High quality costs more and produces a higher-detail result.

Resolution

Default

1152x2048

Options (13)

1152x2048 (Portrait (9:16)), 960x1696 (Portrait (9:16)), 1088x1632 (Portrait (2:3)), 1152x1536 (Portrait (3:4)) +9 more

Seed

Number

Default

-1

Use -1 for a random result or set a seed for repeatable variations.

Style

Select

Default

Creatures

Options (9)

Creatures, Realistic, iPhone, Digital Cam +5 more

Creative preset applied to the reference image.

Style Strength

Number

Default

1

How strongly the selected style changes the reference image.

Benchmarks

No benchmark data is available yet for this model.

Examples

Loading examples…

Compare Higgsfield Soul Image-to-Image with similar models from the same provider or model family.

Higgsfield Soul

higgsfield-soul

Higgsfield Soul generates 4 images per request with various artistic styles including realistic, Y2K, anime, grunge, and more. Offers both basic (720p) and high (1080p) quality options. Takes quite long to generate.

BiRefNet V2

fal-ai/birefnet/v2

Remove backgrounds with dedicated foreground segmentation, preserving transparent edges. Optionally return the mask itself.

GPT Image 2.5 Flare Edit

openai/gpt-image-2.5/flare/edit

GPT Image 2.5 Flare edits images from natural-language instructions with up to 16 reference images. Supports quality levels from low to max and 1K, 2K, or 4K output. Pricing depends on quality, resolution, and reference image count.

GPT Image 2.5 Flare

openai/gpt-image-2.5/flare/text-to-image

GPT Image 2.5 Flare generates images from text prompts or edits images with up to 16 reference images. Supports quality levels from low to max and 1K, 2K, or 4K output. Pricing depends on quality, resolution, and reference image count.

GPT Image 2.5 Sunburst Edit

openai/gpt-image-2.5/sunburst/edit

GPT Image 2.5 Sunburst edits images from natural-language instructions with up to 16 reference images. Supports quality levels from low to max and 1K, 2K, or 4K output. Pricing depends on quality, resolution, and reference image count.

GPT Image 2.5 Sunburst

openai/gpt-image-2.5/sunburst/text-to-image

GPT Image 2.5 Sunburst generates images from text prompts or edits images with up to 16 reference images. Supports quality levels from low to max and 1K, 2K, or 4K output. Pricing depends on quality, resolution, and reference image count.