← Back to all generators

sourceful/riverflow-2.0-fast

Agentic image model optimized for high-quality, fast generations supporting font control

Capabilities

No capability data available

Cost

Community model (estimated from hardware time)

Input Parameters

instruction required string

Generation instruction (text-to-image or edit). Minimum 2 characters.

aspect_ratio string

Aspect ratio for output. auto uses model choice.

Default: "auto"
auto 21:9 16:9 3:2 4:3 5:4 1:1 4:5 3:4 2:3 9:16
enhance_prompt boolean

Let model enhance the instruction.

Default: false
font_texts array

Text strings matching font_urls (≤300 chars each).

font_urls array

Optional font URLs (ttf/otf/woff/woff2). Up to 2.

init_images array

Optional init images (i2i). URLs or uploads. Pro: up to 10, Fast: up to 4.

max_iterations integer

Number of internal reasoning iterations (1-3).

Default: 1 min: 1, max: 3
output_format string

Output image format. API returns webp; png will be converted in Python.

Default: "webp"
webp png
resolution string

Target resolution: 1K or 2K.

Default: "1K"
1K 2K
safety_checker boolean

Enable Sourceful safety checker (t2i).

Default: true
super_resolution_refs array

Optional reference images for detail fix (up to 4). Used in i2i and refsr.

transparency boolean

Enable transparent background when supported.

Default: false
Version: a1af72ca3c83 Updated: 6/26/2026 6.3K runs