How do I pin where text goes in a generated graphic using structured controls (FLUX 3 layout boxes, Recraft V3 text_layout), and which scripts and characters do they support?
Problem. Prompt-only placement drifts; some APIs accept coordinates. Conditions. FLUX 3 Image (BFL) and Recraft V3 / V3 Vector. Method (documented). FLUX 3: a layout prompt is a caption plus a JSON array of elements, each with an id, a bbox and a desc; give each text block its own row, quote the words, and state case, colour and typeface character in the desc; the caption cites the element by its id. A \n inside the quoted string is a line break; 'arranged vertically' sets reading direction. BFL's examples include Japanese and English text on one poster. Recraft: text_layout is an array of {text, bbox} where each item is one word and bbox is four relative points (0,0 top-left, 1,1 bottom-right); coordinates beyond 0 to 1 crop the shape; the field works on V3 and V3 vector models only (the V4/V4.1/V2 columns in the parameter table show no support); the text characters allowed are uppercase Latin letters, digits, basic punctuation, a handful of Latin-extended, Greek and Cyrillic capit...
Structured fields
{
"citations": [
{
"url": "https://docs.bfl.ml/guides/prompting_unified_style.md",
"note": "Text in Images; Tokyo poster; Text in Images; Describe each element; Generate image parameters; Text Layout; Generate image parameters; Text Layout; Text Layout characters"
},
{
"url": "https://docs.bfl.ml/guides/prompting_layout.md",
"note": "Text in Images; Tokyo poster; Text in Images; Describe each element; Generate image parameters; Text Layout; Generate image parameters; Text Layout; Text Layout characters"
},
{
"url": "https://www.recraft.ai/docs/api-reference/agents.md",
"note": "Text in Images; Tokyo poster; Text in Images; Describe each element; Generate image parameters; Text Layout; Generate image parameters; Text Layout; Text Layout characters"
},
{
"url": "https://www.recraft.ai/docs/api-reference/endpoints.md",
"note": "Text in Images; Tokyo poster; Text in Images; Describe each element; Generate image parameters; Text Layout; Generate image parameters; Text Layout; Text Layout characters"
}
]
}Evidence claims
- [sourced_fact] Problem. Prompt-only placement drifts; some APIs accept coordinates. Conditions. FLUX 3 Image (BFL) and Recraft V3 / V3 Vector. Method (documented). FLUX 3: a layout prompt is a caption plus a JSON array of elements, each with an id, a bbox and a desc; give each text block its own row, quote the words, and state case, colour and typeface character in the desc; the caption cites the element by its id. A \n inside the quoted string is a line break; 'arranged vertically' sets reading direction. BFL's examples include Japanese and English text on one poster. Recraft: text_layout is an array of {text, bbox} where each item is one word and bbox is four relative points (0,0 top-left, 1,1 bottom-right); coordinates beyond 0 to 1 crop the shape; the field works on V3 and V3 vector models only (the V4/V4.1/V2 columns in the parameter table show no support); the text characters allowed are uppercase Latin letters, digits, basic punctuation, a handful of Latin-extended, Greek and Cyrillic capitals and the German sharp s, with no CJK in the list. Use [inference]: choose FLUX 3 boxes when the layout includes non-Latin scripts; use Recraft text_layout for short uppercase Latin words on V3; for lowercase body copy, longer text or exact brand type use real type over the image (C3-B593-03). Failure modes. Box too small for the words (inference); one-word-per-item limits phrase kerning; an unsupported character is rejected by the Recraft field rather than rendered. Limitations. I did not call either API; claims about rendering quality inside boxes are the vendors' examples, not tested. Version/date. 2026-10-23. · locator: Text in Images; Tokyo poster; Text in Images; Describe each element; Generate image parameters; Text Layout; Generate image parameters; Text Layout; Text Layout characters source
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Applies to this original summary only, not to the cited sources. |