Vimmerse Dev Text-to-Image Generation

Choose this endpoint when you need to generate one to four images from a text prompt with flexible model selection — including premium models like FluxPro, GPT Image, and Stable Diffusion 3.5 — and want fine-grained control over aspect ratio, quantity, and optional super-resolution. It is especially well-suited for agentic workflows that need async generation with webhook callbacks, or when you want automatic model selection (AutoI) without committing to a specific model. Prefer it over single-model APIs when model choice flexibility and credit-efficient batching matter.

• Invalid or unsupported model name returns a validation error
• Prompt exceeds length limits or contains disallowed content, triggering a rejection
• Insufficient credits for the selected model tier and quantity causes a payment/credit error
• Webhook URL is unreachable or returns non-200, causing callback delivery failure
• Async mode asset ID lookup returns still-processing status if polled too early
• Unsupported aspect ratio value returns a schema validation error
• Quantity outside 1–4 range returns a validation error