Sourceful's fast and cost-efficient image editing model optimized for speed and accessibility, delivering performance close to Riverflow 1 across most editing tasks
Example outputs coming soon
Details
riverflow-1-mini
Providers & Pricing (1)
Riverflow 1 Mini is available exclusively through Runware, starting at $0.032/image.
runware/riverflow-1-mini
Riverflow 1 Mini API OpenAI-compatible
Integrate Riverflow 1 Mini through the Lumenfall OpenAI-compatible API to generate high-speed images and perform cost-efficient image editing within any application.
https://api.lumenfall.ai/openai/v1
riverflow-1-mini
Text to Image Generate
Create images from text descriptions
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-1-mini", "prompt": "A serene mountain landscape at sunset", "size": "1024x1024" }'# Response:# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }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-1-mini', prompt: 'A serene mountain landscape at sunset', size: '1024x1024'});// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }console.log(response.data[0].url);from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.lumenfall.ai/openai/v1")response = client.images.generate( model="riverflow-1-mini", prompt="A serene mountain landscape at sunset", size="1024x1024")# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }print(response.data[0].url)Image Editing Edit
Transform existing images with text instructions
curl -X POST \ https://api.lumenfall.ai/openai/v1/images/edits \ -H "Authorization: Bearer $LUMENFALL_API_KEY" \ -F "model=riverflow-1-mini" \ -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-1-mini', 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 OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.lumenfall.ai/openai/v1")response = client.images.edit( model="riverflow-1-mini", 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)Gallery
View all 1 imagesRiverflow 1 Mini FAQ
Riverflow 1 Mini starts at $0.032 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.
You can use Riverflow 1 Mini through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "riverflow-1-mini". Code examples are available in Python, JavaScript, and cURL.
Riverflow 1 Mini is available through Runware on Lumenfall. Lumenfall automatically routes requests to the best available provider.
Riverflow 1 Mini supports images up to 1024x1024 resolution.
Overview
Riverflow 1 Mini is a lightweight, high-speed image editing model developed by Sourceful. Designed as a streamlined version of the full Riverflow 1 architecture, it focuses on delivering low-latency text-to-image and image-to-image modifications without the computational overhead of larger diffusion models. It bridges the gap between efficiency and quality, maintaining high fidelity across common editing operations while significantly reducing inference costs.
Strengths
- Inference Speed: Optimized for near-instantaneous processing, making it suitable for real-time applications and iterative design workflows where rapid feedback is required.
- Instruction Following: High accuracy in mapping natural language descriptions to visual changes, particularly for localized edits such as object insertion or color modification.
- Resource Efficiency: Occupies a smaller memory footprint than its flagship counterpart, allowing for high-throughput scaling at a lower price point ($0.032 starting price).
- Visual Consistency: Effectively retains the semantic structure and composition of the original input image during the editing process, minimizing unwanted global artifacts.
Limitations
- Complex Composition: May struggle with intricate multi-subject scenes or highly specific spatial relationships compared to the full-scale Riverflow 1 model.
- Fine Detail Grains: While effective for most tasks, the “Mini” architecture may exhibit slightly less texture sharpness or finer detail resolution in extremely high-resolution outputs.
- Extreme Stylization: Large-scale stylistic overhauls that require deep structural reimagining may result in less coherent outputs than larger, more parameter-heavy models.
Technical Background
Riverflow 1 Mini belongs to the Riverflow family of generative models, utilizing a specialized architecture optimized for image-to-image transformations. It leverages a distilled training approach where the model learns to approximate the performance of larger teacher models while operating on a reduced parameter count. This architectural choice prioritizes throughput and accessibility, specifically targeting the Runware infrastructure for optimized hardware utilization.
Best For
Riverflow 1 Mini is ideal for developers building consumer-facing photo editing tools, e-commerce assets, or social media content generators that require high volume and low costs. It excels in tasks like background replacement, object recoloring, and simple guided text-to-image generation. This model is available directly through Lumenfall’s unified API and playground, allowing for seamless integration into existing image processing pipelines alongside other leading generative models.
Try Riverflow 1 Mini in Playground
Generate images with custom prompts — no API key needed.