Image Models

banana-pro — High-quality text-to-image model (optional 1 reference image). Good for detailed key visuals, product shots, and brand-style imagery.
banana2 — General text-to-image model (optional 1 reference image), prioritizing speed and cost. Good for quick drafts, social posts, and multi-ratio generation.
gpt-image-2 — GPT Image 2 model for text-to-image and image editing. Supports generating images from text as well as editing and synthesizing images with reference inputs.
grok-4.2 — Minimalist text-to-image model, prompt-only. Good for quick concept validation or undemanding instant generation.
image-replicate — Image replicate tool: analyzes the source's composition, color, lighting, and style, then uses Seedream 4.5 to generate a new image in the same style.
imageseg — Image matting tool: separates foreground and returns a transparent-background URL. Good for product images, cutouts, and compositing.
jimeng-t2i — Jimeng high-res text-to-image model with multi-ratio ultra-HD output and reference-image constraints. Good for commercial visuals and refined output.
kling-image-o1 — Kling image model, supports '<image_1>' placeholder in prompt for reference image binding. Suitable for multi-image constraints and high-fidelity generation.
mj-imagine — Midjourney style generation, supports aspect ratio, Bot type, and output position (grid/U1-U4). Suitable for artistic and strongly stylized creative generation.
qwen-image-2-pro — Alibaba Bailian qwen-image-2.0-pro general image generation. Excels at complex text rendering, multi-line layout, photorealistic detail, and strong semantic adherence — great for mixed text/image designs.
recraft-v4 — 1MP raster image generation with refined design judgment. Suitable for everyday creative work and fast iteration.
recraft-v4-pro — 4MP high-resolution raster image generation. Suitable for print-ready assets and large-scale use.
recraft-v4-pro-vector — High-fidelity text-to-vector model, 4MP-tier quality. Good for production SVG assets and detailed illustrations.
recraft-v4-vector — Text-to-vector model that outputs SVG results. Suitable for logos, icons, and scalable design assets.
seedream-4.5 — High-quality text-to-image/image-to-image model, suitable for posters, realism, and creative scenes. Supports prompt + multiple reference images, outputting single high-res images (2K/4K).
seedream-5.0-lite — Lightweight high-speed image generation model, suitable for batch generation, sketches, and low-cost iteration. Supports prompt + reference images, outputting 2K/3K images.
superres — Image super-resolution tool: enhances image clarity and details, returning enhanced URL, suitable for low-res asset restoration and upscaling.
vectorize — Image-to-SVG tool: converts raster images (PNG/JPG) into color vector SVG and returns the URL, suitable for lossless scaling and vectorization of logos, icons, and flat illustrations.
video-frame — Video frame extraction tool: captures a single frame from the video by mode (first, last, or a given time) and returns the uploaded image URL.
viduq2-t2i — Vidu image model with text + reference image, ratio, and resolution control. Good for character art, covers, and high-res output.