Sourceful: Riverflow V2.6 Pro
sourceful/riverflow-v2.6-pro
Riverflow 2.6 Pro is the flagship model of Sourceful's Riverflow 2.6 lineup, a unified text-to-image and image-to-image family that treats generation as a production workflow: an integrated reasoning model plans multi-step edits and judges candidates before accepting a result, combining that reasoning with a mix of closed and open image diffusion models for accuracy and steerability. Reasoning effort is controllable via the reasoning parameter (low/medium/high/xhigh); higher levels do more editing passes and apply a stricter internal judge.
Riverflow 2.6 adds custom output dimensions: pass size as WIDTHxHEIGHT (up to 16,384 px per edge, 16.8 megapixels total, 16:1 aspect ratio) instead of a preset, or keep using 1K/2K/4K with an aspect ratio (now including 5:4 and 4:5). It accepts up to 10 input images for editing.
Pricing is dynamic: cost is finalized per job at completion based on billable processing, so it scales with reasoning effort, output size, and editing complexity rather than a fixed per-image rate.
Additional features (via image_config):
- Custom font rendering via font_inputs (max 2) to match brand lettering, spacing, and weight
- Custom scoring via scoring_prompt and scoring_rubric, so the reasoning model evaluates and steers each candidate against the criteria you care about
- Background control via background_mode (original, transparent, solid) and background_hex_color
See the image generation docs for details: https://openrouter.ai/docs/features/multimodal/image-generationOpens in new tab
Note: Sourceful imposes a 4.5MB request size limit, therefore it is highly recommended to pass image URLs instead of Base64 data.
Example outputs summary for Sourceful: Riverflow V2.6 Pro
- Snowy night: Editorial architectural photograph of a contemporary neighborhood storefront on a snowy winter evening at blue hour, glowing warmly against the dusk as snow falls. Above the entrance, a warm-white neon sign in flowing hand-bent cursive reads exactly "OpenRouter", the only text in the scene. Fresh snow blankets the awning, window ledges and sidewalk, and soft snowflakes drift through the golden light spilling from the large windows, which reveal a cozy, lived-in interior: wood shelves styled with books and ceramics, lush trailing plants, and soft pendant lighting. Delicate frost edges the glass, potted boxwood shrubs and a snow-dusted bicycle rest by the entrance. Straight-on composition, realistic materials, quiet street with no people, no holiday decorations. — generated with Sourceful: Riverflow V2.6 Pro
- Twilight: Editorial architectural photograph of a contemporary neighborhood storefront at blue hour, glowing warmly against the dusk. Above the entrance, a warm-white neon sign in flowing hand-bent cursive reads exactly "OpenRouter", the only text in the scene. Large windows reveal a cozy, lived-in interior: wood shelves styled with books and ceramics, lush trailing plants, and soft pendant lighting. Potted plants and a bicycle rest by the entrance, and golden light spills across the wet pavement in gentle reflections. Straight-on composition, realistic materials, quiet street with no people. — generated with Sourceful: Riverflow V2.6 Pro
- Flower shop: Transform this storefront into a tasteful neighborhood flower shop on a bright, dry late-spring morning. Replace the shop interior and window display with a restrained, realistic selection of bouquets, potted flowers, and greenery, with a few organized flower buckets near the entrance. Make the sky and street clearly daytime, remove all wet pavement and reflections, use soft natural sunlight and realistic shadows, and turn off the neon glow while keeping the physical sign and the text "OpenRouter" perfectly clear and readable. Preserve the exact camera angle, framing, architecture, windows, door, bicycle, and surrounding buildings. Keep the result photorealistic and editorial, not overly decorated. — generated with Sourceful: Riverflow V2.6 Pro
Not currently available through EU in-region routing. In-region routing docs