GPT Image 1.5 balances performance and quality with transparent background support. Supports preset resolutions up to 1536x1024. Default quality is low when omitted.
GPT Image 2 is the state-of-the-art image generation model for fast, high-quality image generation. Uses the size parameter for output dimensions including 2K (2048x2048, 2048x1152) and 4K (3840x2160, 2160x3840). Default quality is low when omitted. Does not support transparent backgrounds.
Kling V3 text-to-image model with improved prompt adherence and 1K/2K output support for higher-fidelity creative generation.
Wan 2.7 Image is the standard text-to-image model with faster generation speed. Supports up to 2K resolution, thinking mode, sequential generation, and custom color themes. Does not support 4K.
Wan 2.7 Image Pro is the professional text-to-image model supporting up to 4K resolution, thinking mode for enhanced reasoning, sequential multi-image generation, and custom color themes. Supports Chinese and English prompts up to 5000 characters.
Z-Image Turbo is a lightweight text-to-image model that quickly generates images with Chinese and English text rendering support. It always outputs 1 PNG image per request.
Qwen-Image 2.0 Pro is the most capable model in the Qwen-Image series, with superior text rendering, realistic textures, and semantic adherence. Supports larger resolutions and batch generation of 1-6 images.
Qwen-Image 2.0 is an accelerated model balancing quality and speed. Supports larger resolutions (up to 2688*1536) and batch generation of 1-6 images per request.
Qwen-Image Max produces highly realistic images with reduced AI artifacts. It uses fixed resolution options and generates 1 image per request.