Riverflow 2.0 Fast is the Fast profile of Sourceful’s Riverflow 2.0 image generation and editing family. It is useful for exploring a visual direction or carrying out a clearly specified edit before refining the selected creative. The family adds reasoning-led candidate review and correction to image generation, with attention to brand typography and product detail. Pro is the separate profile for quality-sensitive work within the same generation.
Prepare a focused brief with the subject, setting, lighting and one visual change to explore. A practical early-stage task can place a product pouch on a kitchen surface, leaving a defined area for a headline. Supply the reference that establishes the pouch shape, colour and label, then describe the environment rather than asking for an entirely unspecified advertisement. Keep important product features fixed when comparing different settings or crops.
For editing, state the requested change directly and identify the surrounding details that should stay intact. Replacing a background, adjusting the composition or changing a supporting prop should not make the main product a new SKU. The 2.0 family reviews candidates and makes corrections over multiple steps, so the brief needs a concrete target rather than a general request for a nicer image. Retain the source image when inspecting whether the change preserved the object and its visible wording.
The family’s font-control workflow supports public or supplied custom fonts, with up to two fonts and 300 characters per image in the 2.0 release. Give the exact words and the typographic role of each block. A headline and a small caption can define a useful hierarchy without making the whole canvas a dense document. Check spelling, numbers, spacing and small lettering at the intended display size. A rendered caption is visual content, not a replacement for an editable design file.
For detail problems that remain in a generated scene, the separate 2.0 reference-based super-resolution workflow can use high-quality artwork to repair product text and label details. The release describes up to four replacement instances, whether on one product or across several in the composition. Preserve the original artwork so a repair is guided by the actual design. This is a later detail-preservation stage around the image, not an instruction to assume that every first candidate is already exact.
A useful asset set keeps lighting, visual style and product references consistent while varying the intended scene or placement. For a catalogue, record the image’s product reference and brief alongside the selected output. For a campaign, compare whether the crop leaves room for approved copy and whether the product remains recognisable. Choose which candidate to refine based on the actual task instead of losing the original requirements as the visual direction develops.
Fast remains distinct from Pro and from Riverflow 2.5’s newer custom-judging controls. A focused follow-up can correct a label, remove a supporting object or adjust the arrangement while retaining the successful parts of the scene. The useful deliverable is a selected image connected to its source and intended placement, with later typographic or detail repair guided by the original artwork and the specific detail that needs correction.
", "aboutText": "Riverflow 2.0 Fast is the Fast profile of Sourceful’s Riverflow 2.0 image generation and editing family. It is useful for exploring a visual direction or carrying out a clearly specified edit before refining the selected creative. The family adds reasoning-led candidate review and correction to image generation, with attention to brand typography and product detail. Pro is the separate profile for quality-sensitive work within the same generation.\n\nPrepare a focused brief with the subject, setting, lighting and one visual change to explore. A practical early-stage task can place a product pouch on a kitchen surface, leaving a defined area for a headline. Supply the reference that establishes the pouch shape, colour and label, then describe the environment rather than asking for an entirely unspecified advertisement. Keep important product features fixed when comparing different settings or crops.\n\nFor editing, state the requested change directly and identify the surrounding details that should stay intact. Replacing a background, adjusting the composition or changing a supporting prop should not make the main product a new SKU. The 2.0 family reviews candidates and makes corrections over multiple steps, so the brief needs a concrete target rather than a general request for a nicer image. Retain the source image when inspecting whether the change preserved the object and its visible wording.\n\nThe family’s font-control workflow supports public or supplied custom fonts, with up to two fonts and 300 characters per image in the 2.0 release. Give the exact words and the typographic role of each block. A headline and a small caption can define a useful hierarchy without making the whole canvas a dense document. Check spelling, numbers, spacing and small lettering at the intended display size. A rendered caption is visual content, not a replacement for an editable design file.\n\nFor detail problems that remain in a generated scene, the separate 2.0 reference-based super-resolution workflow can use high-quality artwork to repair product text and label details. The release describes up to four replacement instances, whether on one product or across several in the composition. Preserve the original artwork so a repair is guided by the actual design. This is a later detail-preservation stage around the image, not an instruction to assume that every first candidate is already exact.\n\nA useful asset set keeps lighting, visual style and product references consistent while varying the intended scene or placement. For a catalogue, record the image’s product reference and brief alongside the selected output. For a campaign, compare whether the crop leaves room for approved copy and whether the product remains recognisable. Choose which candidate to refine based on the actual task instead of losing the original requirements as the visual direction develops.\n\nFast remains distinct from Pro and from Riverflow 2.5’s newer custom-judging controls. A focused follow-up can correct a label, remove a supporting object or adjust the arrangement while retaining the successful parts of the scene. The useful deliverable is a selected image connected to its source and intended placement, with later typographic or detail repair guided by the original artwork and the specific detail that needs correction.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "2d6557e3e79dd42f768656fb4a8bc8a3ccc295616692e38b8a3aba7efe218518", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "sourceful/riverflow-v2-fastRiverflow 2.0 Fast is Sourceful’s Fast profile for image creation and focused visual edits. Use clear product and style references to explore marketing imagery within a multi-step workflow that reviews candidates and preserves typography and detail.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Riverflow 2.0 Fast is the Fast profile of Sourceful’s Riverflow 2.0 image generation and editing family. It is useful for exploring a visual direction or carrying out a clearly specified edit before refining the selected creative. The family adds reasoning-led candidate review and correction to image generation, with attention to brand typography and product detail. Pro is the separate profile for quality-sensitive work within the same generation.
Prepare a focused brief with the subject, setting, lighting and one visual change to explore. A practical early-stage task can place a product pouch on a kitchen surface, leaving a defined area for a headline. Supply the reference that establishes the pouch shape, colour and label, then describe the environment rather than asking for an entirely unspecified advertisement. Keep important product features fixed when comparing different settings or crops.
For editing, state the requested change directly and identify the surrounding details that should stay intact. Replacing a background, adjusting the composition or changing a supporting prop should not make the main product a new SKU. The 2.0 family reviews candidates and makes corrections over multiple steps, so the brief needs a concrete target rather than a general request for a nicer image. Retain the source image when inspecting whether the change preserved the object and its visible wording.
The family’s font-control workflow supports public or supplied custom fonts, with up to two fonts and 300 characters per image in the 2.0 release. Give the exact words and the typographic role of each block. A headline and a small caption can define a useful hierarchy without making the whole canvas a dense document. Check spelling, numbers, spacing and small lettering at the intended display size. A rendered caption is visual content, not a replacement for an editable design file.
For detail problems that remain in a generated scene, the separate 2.0 reference-based super-resolution workflow can use high-quality artwork to repair product text and label details. The release describes up to four replacement instances, whether on one product or across several in the composition. Preserve the original artwork so a repair is guided by the actual design. This is a later detail-preservation stage around the image, not an instruction to assume that every first candidate is already exact.
A useful asset set keeps lighting, visual style and product references consistent while varying the intended scene or placement. For a catalogue, record the image’s product reference and brief alongside the selected output. For a campaign, compare whether the crop leaves room for approved copy and whether the product remains recognisable. Choose which candidate to refine based on the actual task instead of losing the original requirements as the visual direction develops.
Fast remains distinct from Pro and from Riverflow 2.5’s newer custom-judging controls. A focused follow-up can correct a label, remove a supporting object or adjust the arrangement while retaining the successful parts of the scene. The useful deliverable is a selected image connected to its source and intended placement, with later typographic or detail repair guided by the original artwork and the specific detail that needs correction.
POST /v1/images/generationstext, imageimage| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits sourceful/riverflow-v2-fast | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldresolution | Typestring | RequirementOptional | Values & limits 1K, 2K, 4K | Default— |
Fieldaspect_ratio | Typestring | RequirementOptional | Values & limits 1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, auto | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Maximum: 1 | Default— |
Fieldinput_references | Typearray | RequirementOptional | Values & limits Minimum items: 0 Maximum items: 4 | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt |
Parametermaterial_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}
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.
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 $0.04 per output image |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Billing unit— | Charge Output · Estimated generation cost · Estimate for comparison only $0.04 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'model': 'sourceful/riverflow-v2-fast', 'prompt': 'a red panda astronaut floating in space, studio lighting'}\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n 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"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nDownload each returned image or save its Base64 contents
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\nSave every completed image; retrieve each returned URL or decode its Base64 contents.
Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.
Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation.
| Field | Type |
|---|---|
Fieldcreated | Type |
Fielddata[].url | Type |
Fielddata[].b64_json | Type |
Fieldusage | Type |
Ailoot Ultra sourceful/riverflow-v2-fast
/v1/images