Source: https://ailoot.ai/models/en/sourceful-riverflow-v2-pro/ Canonical: https://ailoot.ai/models/en/sourceful-riverflow-v2-pro/ Language: en # Sourceful: Riverflow V2 Pro [Markdown](https://ailoot.ai/models/en/sourceful-riverflow-v2-pro/index.md) · [JSON](https://ailoot.ai/models/en/sourceful-riverflow-v2-pro/facts.json) ## [Sourceful: Riverflow V2 Pro](https://ailoot.ai/models/en/sourceful-riverflow-v2-pro/) Riverflow 2.0 Pro is Sourceful’s Pro image generation and editing profile for brand-sensitive creative. Its family reviews and corrects candidates, supports font guidance and provides reference-based detail repair for product labels and artwork. - [**Ailoot Ultra · Images** `POST /v1/images/generations` `sourceful/riverflow-v2-pro`](https://ailoot.ai/models/en/sourceful-riverflow-v2-pro/#method-0) About the model This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below. Riverflow 2.0 Pro is the Pro profile of Sourceful’s Riverflow 2.0 image generation and editing family for product, packaging and marketing creative. It combines image creation or editing with a reasoning model that reviews candidates and makes corrections. Its defining concerns are reliable execution of a visual brief, typography and preservation of the product details that make an asset useful to a brand. For a quality-sensitive composition, supply the product image or artwork, the exact wording and the intended visual arrangement. A useful scene can place a labelled jar beside its ingredients while preserving the container shape and label hierarchy. Describe the lighting, background and crop, then state which product details should not change. The result is a rendered creative image; deciding how it fits into a wider campaign or an editable layout is a separate application step. The 2.0 workflow automatically assesses candidates and corrects problems over multiple steps. Give that process a clear target by separating required content from optional style choices. For an edit, name the element to change and the surrounding features to retain. A product colour update should not silently become a new label design, and a background replacement should keep the supplied object recognisable. The finished image still needs comparison with the brief and source references. Font control uses public or supplied custom fonts to guide brand typography. Riverflow 2.0 supports up to two fonts at a time and up to 300 characters per image in its font-control workflow. Provide the exact text, hierarchy and intended weight or spacing rather than expecting the model to choose the wording. Inspect important glyphs, numerals, ligatures and small supporting text in the resulting asset. Keeping the wording concise also leaves space for the product and visual explanation. The family’s reference-based super-resolution workflow repairs fine text or artwork that a lower-resolution scene does not contain accurately. Supply high-quality source artwork so the detail-repair stage has the actual label or design to reproduce. The 2.0 release describes up to four replacement instances per request, allowing fixes on one product or several products in a scene. This is a reference-based repair workflow around the generated image, rather than a guarantee that every initial picture has perfect micro-detail. For a related product set, keep the style, lighting and scene structure consistent while supplying the correct reference for each item. A campaign asset can combine a main product view with practical space for approved copy; a product close-up can prioritise label and material detail. Choose the source and output preparation for the intended display size, and preserve the selected image with the references that establish its identity. A scene-level correction and a detail-repair step address different parts of the artifact. Pro is distinct from the Fast profile and from Riverflow 2.5. The later generation adds custom scoring criteria and deeper review controls; those later settings should not be assumed to be part of this 2.0 profile. For a useful final review, check the requested change, typography, product identity and surrounding details against the source. Revise the specific instruction or reference responsible for a mismatch while retaining the composition that already fits the task. **Ailoot Ultra · Images** `POST /v1/images/generations` `sourceful/riverflow-v2-pro` [`sourceful/riverflow-v2-pro`](https://ailoot.ai/models/en/#m=sourceful%2Friverflow-v2-pro&route=Ultra&caller=sourceful%2Friverflow-v2-pro&fmt=images) Sourceful /`sourceful/riverflow-v2-pro` ### Overview Riverflow 2.0 Pro is Sourceful’s Pro image generation and editing profile for brand-sensitive creative. Its family reviews and corrects candidates, supports font guidance and provides reference-based detail repair for product labels and artwork. Accepted inputs Text · Images Results Images ### Available in Ailoot · inputs & methods **Ailoot Ultra · Images** `POST /v1/images/generations` Input types `text`, `image` Output types `image` | Field | Type | Requirement | Values & limits | Default | | --- | --- | --- | --- | --- | | Field`model` | Type`string` | RequirementRequired | Values & limits sourceful/riverflow-v2-pro | Default— | | Field`prompt` | Type`string` | RequirementRequired | Values & limits Minimum length: 1 | Default— | | Field`resolution` | Type`string` | RequirementOptional | Values & limits 1K, 2K, 4K | Default— | | Field`aspect_ratio` | Type`string` | RequirementOptional | Values & limits 1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, auto | Default— | | Field`n` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Maximum: 1 | Default— | | Field`input_references` | Type`array` | RequirementOptional | Values & limits Minimum items: 0 Maximum items: 10 | Default— | | Field`provider` | Type`object` | RequirementOptional | Values & limits | Default— | Method parameters and lifecycle | Parameter | Contract | | --- | --- | | Parameter`content_type` | Contractapplication/json | | Parameter`required` | Contractmodel, prompt | | Parameter`material_types` | Contracttext, image | Lifecycle: `synchronous_result_then_owned_library` `GET /v1/media/tasks/{task_id}` · actual returned task\_id or media library record `GET /v1/media/assets/{asset_id}/content` `GET /v1/media/assets` `GET /v1/media/assets/{asset_id}` ### Pricing ##### How the final charge is calculated The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity. Tariff references do not add request options. Supported parameters are listed for the selected method. Fast mode Not specified When fast mode is selected Flex mode Not specified When flex mode is selected Maximum reasoning effort Not specified When maximum reasoning effort uses the default adjustment #### Estimated rates for comparison #### Prices by configuration Match each charge to the conditions shown. Use one rate for each set of alternative configurations. | Configuration | Rate schedule | Forecast quantity | Billing unit | Charge | | --- | --- | --- | --- | --- | | ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Billing unit— | Charge Input · Input tokens · Estimate for comparison only **—** / 1K tokens Output · Output tokens · Estimate for comparison only **—** / 1K tokens Input · Cache read · Estimate for comparison only **—** / 1K tokens Input · Cache write · Estimate for comparison only **—** / 1K tokens Input · Cache write, 1 hour · Estimate for comparison only **—** / 1K tokens | | ConfigurationFont input | Rate schedule— | Forecast quantity— | Billing unitper image | Charge Input · Font input · Estimate for comparison only **$0.06** per image | | ConfigurationInput reference | Rate schedule— | Forecast quantity— | Billing unitper image | Charge Input · Input reference · Estimate for comparison only **$0.4** per image | | Configurationoutput image | Rate schedule— | Forecast quantity— | Billing unitper output image | Charge Output · output image · Estimate for comparison only **$0.3** per output image | | ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Billing unit— | Charge Output · Estimated generation cost · Estimate for comparison only **$0.3** estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. | Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/) ### Example requests #### Ailoot Ultra · Images curl ```bash set -eu : "${AILOOT_API_KEY:?Set your Ailoot API key}" export AILOOT_API_KEY python3 - <<'PY_REQUEST' import json,os from pathlib import Path p={'model': 'sourceful/riverflow-v2-pro', 'prompt': 'a red panda astronaut floating in space, studio lighting'} Path("request.json").write_text(json.dumps(p,ensure_ascii=False)) PY_REQUEST curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \ -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \ --data-binary @request.json -D response-headers.txt -o result.json python3 - <<'PY_RESULT' import base64, json, os, subprocess from pathlib import Path from urllib.parse import urlsplit, urljoin def save_images(items): if not items: raise SystemExit("No completed images; retain the full response") for index, item in enumerate(items): encoded=item.get("b64_json") uri=item.get("url", "") if not encoded and uri.startswith("data:image/"): header, separator, encoded=uri.partition(",") if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI") if encoded: raw=base64.b64decode(encoded,validate=True) elif uri: uri=urljoin("https://api.ailoot.ai",uri) parsed=urlsplit(uri) if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password: raise SystemExit("Invalid returned image URL") owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content") args=["curl","--fail-with-body","--silent","--show-error",uri] if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]] temporary=Path(f"image-{index}.bin") subprocess.run(args+["-o",str(temporary)],check=True) raw=temporary.read_bytes() temporary.unlink() else: raise SystemExit("Image has neither bytes nor URL") if not raw: raise SystemExit("Empty image result") ext="png" if raw.startswith(b"\x89PNG") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"