AI Image and Video API Platform

Baidu Ernie text-to-image (fal.ai). Multilingual prompts and built-in prompt expansion.

FLUX family on Replicate. Schnell, Dev, Pro, Kontext, Ultra, and LoRA remix variants in one entrypoint.

Max-quality with up to 10 reference images

Very fast generation and editing with up to 5 reference images

4-step distilled FLUX.2 [klein] foundation model for flexible control

High-quality with up to 8 reference images

The highest fidelity image model from Black Forest Labs

Fast quality with up to 4 reference images

Dev model with custom LoRA support

High-quality development model with configurable steps, guidance, and LoRA support.

Photorealistic generation that avoids the oversaturated AI look. LoRA compatible.

Supports multiple custom LoRAs simultaneously for complex style combinations.

Latest pro model with enhanced quality and strong prompt adherence.

Highest quality Flux model with raw mode for natural-looking images.

Advanced model with state-of-the-art performance for both generation and editing.

Premium model with maximum performance and improved typography for generation and editing.

Fast generation with Gemini 2.5 Flash

SOTA with accurate typography and reasoning

Next-generation SOTA model with stronger consistency

Google Nano Banana image editing. Multi-image fusion + edit instruction with Standard/Pro/Pro-fal tiers and 1K/2K/4K resolution.

ByteDance Seedream 3 text-to-image via Replicate.

ByteDance Seedream 4.5 — new-generation image creation with superior aesthetics, text rendering, and up to 4K resolution.

ByteDance Seedream 5.0 Lite — fast, high-quality image generation and editing with strong aesthetics and text rendering.

xAI Grok Imagine. Fast tier for quick iteration, Quality tier for higher fidelity at 1k or 2k.

Z Image Spicy text-to-image. Square / portrait / landscape compositions, 256–1536px on each side.