Models

Kling 3.0 Omni

Flagship unified multimodal model integrating text-to-video, image-to-video, and reference-based generation. Supports up to 15-second cinematic clips with native synchronized audio (dialogue, SFX, BGM). Enables multi-shot control (up to 6 shots) and consistent subject/character preservation across scenes. Pro mode outputs 1080p with enhanced motion realism

kling v3

Next-generation video generation model offering Standard and Pro tiers. Generates 3–15 second clips at up to 1080p resolution from text or image inputs. Features first-frame and last-frame control for precise scene composition. Supports 16:9, 9:16, and 1:1 aspect ratios. Native audio generation available as an optional feature

Seedream 5.0

Supports text, single-image and multi-image inputs, and enables the generation of image sets

Wan 2.7 Image Pro

Wan2.7–image-pro，supports text to image, text/image to sequential images, image editing, multi-image reference generation, and interactive editing. Delivers enhanced performance in text rendering, subject consistency, and complex instruction following.

Kling Image O1

Advanced image generation model from the Kling O1 family. Supports text-to-image and image-to-image workflows with deep semantic understanding. Features character/subject consistency across generations, multi-reference input (up to 7 images), and intelligent aspect ratio adaptation. Professional-grade output suitable for commercial creative pipelines

Qwen Image 2.0 Pro

The full-featured Qwen-Image-2.0 series models integrate image generation and image editing, offering enhanced text rendering with support for 1,000-token prompts, more refined realistic textures, detailed depiction of photorealistic scenes, and stronger semantic adherence. The full-featured version delivers the strongest text rendering and most lifelike textures in the 2.0 series.

MiniMax Image-01

MiniMax’s first text-to-image model with subject reference support. Delivers high-fidelity visuals, detailed lighting, and complex scene composition. Generates realistic human/object renders with natural textures, ideal for concept art, product visualization, and creative design.

Seedream 4.5

Supports text, single-image, and multi-image input, and enables batch image generation.

Seedream 4.0

Supports text, single-image, and multi-image inputs, and enables series image generation.

Vidu Q2 · Image Generation

Next-gen image-to-video model with "emotional acting" for nuanced facial expressions. Supports 2–8s clips at 1080p with cinematic camera control. Features multi-modal reference (2 videos + 4 images) enabling precise replication of expressions, actions, textures, and effects. Includes video editing: element add/delete/replace, style transfer, aspect adjustment. Lightning mode outputs 5s in 20s. Supports up to 7 consistent subjects, 3x faster than Q1

Qwen Image 3.0 Pro

Professional-grade image generation and editing model. Supports text-to-image and image-to-image workflows with precise rendering of text as small as 10px. Generates complex layouts—newspapers, storyboards, menus, exam papers—in a single pass. Native 12-language rendering with rich world knowledge. Input up to 4.5K tokens

Seedream 5.0 Pro

ByteDance's flagship image model for high-precision generation and interactive editing. Supports text-to-image, single-image-to-image, and multi-reference generation (up to 10 images). Core features include interactive editing via coordinates/bboxes, layer separation, sketch-to-image, and native multilingual text rendering for 14+ languages. Outputs up to 2K resolution (png/jpeg) with natural human and material textures