# Riverflow 2 Fast Preview

> Sourceful's lightweight Riverflow 2 variant for fast workflows and lower cost, combining unified text-to-image generation with precise editing capabilities

## Quick Reference

- Model ID: riverflow-2-fast-preview
- Creator: Sourceful
- Status: active
- Family: riverflow
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Max Resolution: 1024x1024
- Max Input Images: 3
- Input Modalities: text, image
- Output Modalities: image

## Model Identifiers

- Primary Slug: riverflow-2-fast-preview
- Aliases: riverflow-2-fast

## Dates


## Tags

image-generation, text-to-image, image-editing

## Available Providers

### Runware

- Config Key: runware/riverflow-2-fast-preview
- Provider Model ID: sourceful:2@2
- Pricing:
  - source: official
  - currency: USD
  - components: [{"type" => "output", "metric" => "image", "unit_price" => 0.03}]
  - source_url: https://runware.ai/pricing
  - effective_at: 2026-01-03


## Image Gallery

4 images available for this model.
- Curated examples: 4
  - "A cinematic, wide-angle shot of a sleek, high-speed luxury yacht cutting through deep turquoise coastal waters at sun..."
  - "A hyper-realistic close-up of a weathered leather workbench, featuring a collection of vintage watchmaking tools, bra..."
  - "A hyper-realistic close-up of an weathered, olive-skinned artisan's hands meticulously carving intricate floral patte..."
  - "A cozy street-side flower shop with a chalkboard sign that says "BLOOM & GROW" in elegant hand-drawn calligraphy. In ..."

## Example Prompt

The following prompt was used to generate an example image in our playground:

A cozy street-side flower shop with a chalkboard sign that says "BLOOM & GROW" in elegant hand-drawn calligraphy. In the soft-focus background, a capybara calmly rests on the cobblestones near a bicycle. Cinematic lighting, 8k, warm tones.

## Code Examples

### Text to Image (Generation)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/generations \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "riverflow-2-fast-preview",
    "prompt": "A serene mountain landscape at sunset",
    "size": "1024x1024"
  }'

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

#### JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.generate({
  model: 'riverflow-2-fast-preview',
  prompt: 'A serene mountain landscape at sunset',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.generate(
    model="riverflow-2-fast-preview",
    prompt="A serene mountain landscape at sunset",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)

### Image Editing

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=riverflow-2-fast-preview" \
  -F "image=@source.png" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"

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

#### JavaScript

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-fast-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);

#### Python

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-fast-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)


## About

## Overview
Riverflow 2 Fast Preview is a lightweight image generation model developed by Sourceful, designed specifically for rapid prototyping and low-latency iteration. It functions as an optimized variant of the standard Riverflow 2 architecture, balancing computational efficiency with high-fidelity output. The model is distinctive for its dual-mode capability, allowing users to perform both initial text-to-image generation and subsequent precise image editing within a single, unified framework.

## Strengths
*   **Low-Latency Generation:** Optimized for speed, making it suitable for real-time applications, live previews, and high-frequency drafting sessions where standard models would be too slow.
*   **Contextual Image Editing:** Unlike models that focus solely on generation, this model handles image-to-image tasks and localized edits while maintaining the stylistic consistency of the original input.
*   **Semantic Alignment:** Demonstrates strong adherence to complex text prompts, ensuring that the visual elements generated accurately reflect descriptive adjectives and spatial relationships.
*   **Resource Efficiency:** Provides a cost-effective alternative for high-volume workflows ($0.03 starting price) without the heavy compute requirements of larger diffusion models.

## Limitations
*   **Fine Detail Resolution:** As a "Fast Preview" variant, it may lack the intricate micro-textures and hyper-realistic skin or surface details found in the full-scale Riverflow 2 model.
*   **Complex Text Rendering:** While proficient at object placement, the model may struggle with rendering long strings of legible text or very small, complex typographical elements within an image.
*   **Compositional Stability:** In highly crowded scenes with many subjects, the model may occasionally introduce anatomical inconsistencies or overlapping artifacts compared to larger, slower models.

## Technical Background
Riverflow 2 Fast Preview belongs to the Riverflow family of models, characterized by an architecture that integrates text-to-image and image-to-image modalities into a single pipeline. The training approach focuses on distillation and weight optimization to reduce inference steps while preserving the latent space's expressive power. This allows the model to process both text and image inputs natively, facilitating seamless transitions between creative generation and iterative refinement.

## Best For
*   **Rapid Prototyping:** Ideal for designers and developers who need to generate a high volume of concepts or "mood board" assets quickly.
*   **Interactive Applications:** Suitable for UI/UX environments where users expect near-instant visual feedback based on prompt changes.
*   **Iterative Editing Workflows:** Effective for tasks where an initial image needs constant, minor adjustments to color, composition, or specific objects.

Riverflow 2 Fast Preview is available for testing and integration through Lumenfall’s unified API and interactive playground, allowing you to compare its performance against other models in the Riverflow family.

## Frequently Asked Questions

### How much does Riverflow 2 Fast Preview cost?

Riverflow 2 Fast Preview starts at $0.03 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### How do I use Riverflow 2 Fast Preview via API?

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

### Which providers offer Riverflow 2 Fast Preview?

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

### What is the maximum resolution for Riverflow 2 Fast Preview?

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

## Links

- Model Page: https://lumenfall.ai/models/sourceful/riverflow-2-fast-preview
- About: https://lumenfall.ai/models/sourceful/riverflow-2-fast-preview/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/sourceful/riverflow-2-fast-preview/providers
- API Reference: https://lumenfall.ai/models/sourceful/riverflow-2-fast-preview/api
- Benchmarks: https://lumenfall.ai/models/sourceful/riverflow-2-fast-preview/benchmarks
- Use Cases: https://lumenfall.ai/models/sourceful/riverflow-2-fast-preview/use-cases
- Gallery: https://lumenfall.ai/models/sourceful/riverflow-2-fast-preview/gallery
- Playground: https://lumenfall.ai/playground?model=riverflow-2-fast-preview
- API Documentation: https://docs.lumenfall.ai