Models
Sourceful
Riverflow 2 Max Preview

Sourceful

Riverflow 2 Max Preview

Name: Riverflow 2 Max Preview
Brand: Sourceful
Price: 0.075 USD
Availability: InStock

AI Image Editing Model

Image

Sourceful's most powerful Riverflow 2 variant with maximum thinking time for highest quality unified text-to-image and image editing output

Try Model

1024 x 1024

Max Resolution

Supported Modes

Image Edit

Active

Details

Model ID

riverflow-2-max-preview

Also known as: riverflow-2-max

Creator

Sourceful

Family

riverflow

Max Input Images

Ready to integrate?

Access riverflow-2-max-preview via our unified API.

Create Account

Available at 1 provider

Starting from

$0.075 /image via Runware

Prices shown are in USD

Full pricing details

Providers & Pricing (1)

Riverflow 2 Max Preview is available exclusively through Runware, starting at $0.075/image.

Runware

runware/riverflow-2-max-preview

Provider Model ID: sourceful:2@3

$0.075 /image

View pricing details

riverflow-2-max API OpenAI-compatible

Lumenfall provides an OpenAI-compatible API to integrate Riverflow 2 Max Preview into workflows for high-fidelity text-to-image generation and complex image editing.

Base URL

https://api.lumenfall.ai/openai/v1

Model

riverflow-2-max-preview

Code Examples

Image Edit

/v1/images/edits

curl -X POST \

  https://api.lumenfall.ai/openai/v1/images/edits \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -F "model=riverflow-2-max-preview" \

  -F "[email protected]" \

  -F "prompt=Add a starry night sky to this image" \

  -F "size=1024x1024"

# Response:

# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

import OpenAI from 'openai';

import fs from 'fs';

const client = new OpenAI({

  apiKey: 'YOUR_API_KEY',

  baseURL: 'https://api.lumenfall.ai/openai/v1'

});

const response = await client.images.edit({

  model: 'riverflow-2-max-preview',

  image: fs.createReadStream('source.png'),

  prompt: 'Add a starry night sky to this image',

  size: '1024x1024'

});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

console.log(response.data[0].url);

from openai import OpenAI

client = OpenAI(

    api_key="YOUR_API_KEY",

    base_url="https://api.lumenfall.ai/openai/v1"

response = client.images.edit(

    model="riverflow-2-max-preview",

    image=open("source.png", "rb"),

    prompt="Add a starry night sky to this image",

    size="1024x1024"

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

print(response.data[0].url)

Parameter Reference

Required Supported Not available

Core Parameters

Parameter	Type	Description	Modes
`prompt`	string	Required. Edit instruction for the image	Edit

Size & Layout

Parameter	Type	Description	Modes
`size`	string	Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9") WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.	Edit
`aspect_ratio`	string	Aspect ratio of the output image (e.g. "16:9", "1:1") Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.	Edit
`resolution`	string	Output resolution tier (e.g. "1K", "4K") Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.	Edit

size

Exact pixel dimensions

"1920x1080"

aspect_ratio

Shape only, default scale

"16:9"

resolution

Scale tier, preserves shape

"1K"

Priority when combined

size › aspect_ratio + resolution › aspect_ratio › resolution

size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.

How matching works

Shape matching – we pick the closest supported ratio. Ask for 7:1 on a model with 4:1 and 8:1, you get 8:1.

Scale matching – providers use different tier formats: K tiers (0.5K 1K 2K 4K) or megapixel tiers (0.25 1). If the exact tier isn't available, you get the nearest one.

Dimension clamping – if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.

Media Inputs

Parameter	Type	Description	Modes
`image`	file	Required. Input image(s) to edit Supports PNG, JPEG, WebP.	Edit

Output & Format

Parameter	Type	Description	Modes
`response_format`	string	How to return the image `url` `b64_json` Default: `"url"`	Edit
`output_format`	string	Output image format `png` `jpeg` `gif` `webp` `avif` Gateway converts to requested format if provider doesn't support it natively.	Edit
`output_compression`	integer	Compression level for lossy formats (JPEG, WebP, AVIF)	Edit
`n`	integer	Number of images to generate Default: `1` Gateway generates multiple images in parallel even if provider only supports 1.	Edit

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior	What happens	Example
`passthrough`	Sent as-is to the provider	style, quality
`renamed`	Same value, mapped to the field name the provider expects	prompt
`converted`	Transformed to the provider's native format	size
`emulated`	Works even if the provider has no concept of it	n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.

Full API Reference Authentication, endpoints, and more

Gallery

View all 2 images

Riverflow 2 Max Preview FAQ

How much does Riverflow 2 Max Preview cost?

Riverflow 2 Max Preview starts at $0.075 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

How do I use Riverflow 2 Max Preview via API?

You can use Riverflow 2 Max Preview through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "riverflow-2-max-preview". Code examples are available in Python, JavaScript, and cURL.

Which providers offer Riverflow 2 Max Preview?

Riverflow 2 Max Preview is available through Runware on Lumenfall. Lumenfall automatically routes requests to the best available provider.

What is the maximum resolution for Riverflow 2 Max Preview?

Riverflow 2 Max Preview supports images up to 1024x1024 resolution.

Overview

Riverflow 2 Max Preview is the high-performance variant of Sourceful’s latest diffusion model family, designed for unified text-to-image generation and complex image editing. This version is distinguished by an extended internal processing overhead, referred to by the developers as “maximum thinking time,” which prioritizes output fidelity over inference speed. It operates on a unified architecture that allows it to handle both initial generation and modification tasks within a single framework.

Strengths

Text Rendering Accuracy: The model demonstrates high precision when integrating legible typography and specific graphical text into generated images, reducing the common artifacting seen in shorter-latency models.
Unified Task Handling: Unlike models that require separate adapters for editing, Riverflow 2 Max handles text-to-image, image-to-image, and selective editing natively, maintaining stylistic consistency across iterative changes.
Compositional Detail: The extended processing time allows the model to better resolve complex spatial relationships and crowded scenes described in long-form prompts.
Instruction Following: It excels at adhering to nuanced modifiers regarding lighting, texture, and camera perspective, making it suitable for professional design workflows where specific artistic control is required.

Limitations

Inference Latency: Due to its “maximum thinking time” design, this model has a significantly slower generation speed compared to the standard Riverflow 2 or the “Flash” variants, making it less suitable for real-time applications.
Resource Intensity: The computational cost per image is higher, as reflected by its starting price point relative to smaller or less intensive diffusion models.
Preview Status: As a preview release, the model may exhibit occasional inconsistencies in edge cases that are still being refined for the final stable release.

Technical Background

Riverflow 2 Max is built on a consolidated latent diffusion architecture that treats image generation and editing as a single objective. By increasing the iterative refinement steps—Sourceful’s “thinking time” approach—the model explores a wider search space within the latent manifold before decoding the final image. This provides the transformer-based backbone more cycles to align the visual output with the input tokens and any provided image reference.

Best For

Riverflow 2 Max Preview is ideal for high-stakes creative production where image quality and prompt adherence are more critical than rapid throughput. It shines in professional graphic design, advertising asset creation, and complex photo manipulation tasks. Users can explore its capabilities and integrate it into their workflows via Lumenfall’s unified API and interactive playground, which provides a streamlined interface for testing its maximum thinking time outputs alongside other models in the Riverflow family.

Try Riverflow 2 Max Preview in Playground

Generate images with custom prompts — no API key needed.

Open Playground