Modèles d'image

GPT-Image-2 is OpenAI's next-generation image model for stronger photorealism, cleaner image editing, and sharper in-image text rendering.

BFL’s latest Pro & Flex pipelines for text-to-image and image-to-image with unified 1K/2K pricing and ~30s generation.

Qwen Image 3.0 is Alibaba's text-to-image and image-to-image model with 1K and 2K output, fifteen aspect ratios, up to three reference images, and optional prompt expansion. Both resolution tiers are billed at the same rate.

Qwen Image 3.0 Pro is Alibaba's higher-tier route for the same text-to-image and image-to-image contract, pricing 1K and 2K output separately so drafts and final deliverables can be billed differently.

Seedream 5.0 Pro is ByteDance's premium single-image model for text-to-image and image-to-image generation, supporting 1K/2K resolution, eight aspect ratios, up to 10 reference images, and strict custom-size control.

Wan 2.7 Image is Alibaba's omni-image API for text-to-image, reference-guided image generation, image editing, sequential images, and high-resolution Omni Image Pro workflows.

Seedream 5.0 is ByteDance's next-generation AI image model with real-time web search, controllable editing, and logical reasoning. It supports text-to-image and image-to-image with 2K/3K resolution, multiple aspect ratios, and up to 14 reference images.

Image Upscaler is APIXO's single-image enhancement API for 2K, 4K, and 8K upscaling with JPG, PNG, and WEBP output format control.

Image Watermark Remover is APIXO's authorized single-image cleanup API for removing sample marks or overlays from images you own or have permission to process.

Wan 2.5 Image is Alibaba's batch-friendly image generation model for text-to-image and image-to-image workflows, defaulting to four generated images per request.

Wan 2.6 Image is Alibaba's text-to-image and image-to-image model with prompt, negative prompt, aspect ratio, batch count, and optional seed control.

MiniMax Image 01 is MiniMax’s text-to-image and image-to-image model with prompt optimization, flexible size control, 1K/2K presets, and up to 9 generated images per task.

Grok Image is xAI's image generation model for text-to-image and image-to-image workflows with simple aspect-ratio control and async task delivery. Text-to-image returns 6 images per request on APIXO.

Nano Banana 2 is Google’s high-resolution image generation model with 1K/2K/4K output control, 20,000-character prompts, and support for up to 14 reference images. Google Search context is not exposed as an active control in APIXO’s current route.

Nano Banana Pro is Google’s Gemini 3 Pro Image route for reasoning-informed image generation, native 4K output, multilingual typography, and spatially precise compositions. APIXO does not expose Search Grounding as an active control on this route.

Midjourney is an advanced AI image generation model known for artistic, high-quality outputs. It supports text-to-image, image-to-image, image-edit, Vary, and Upscale workflows.

Professional-grade image generation with enhanced prompt understanding and superior quality output.

GPT-Image-1 is OpenAI's advanced multimodal model for high-quality image generation with natural language understanding.

Gemini 2.5 Flash Image Preview (aka Nano Banana) is an advanced AI model excelling in natural language-driven image generation and editing. It produces hyper-realistic, physics-aware visuals with seamless style transformations.

Seedream 4.5 is a powerful text-to-image and image-to-image AI model delivering high-quality image generation with support for 2K and 4K resolutions.