Qwen-Image
Qwen-Image is an open-weight diffusion transformer image generation model from Alibaba's Qwen team, notable for its strong text rendering accuracy and multilingual typography — including precise layout across English, Chinese, and other scripts. It integrates a vision-language encoder for deep prompt understanding and supports a wide range of artistic styles, from photorealistic scenes to illustrations, with unified generation and editing capabilities in a single model.
Features
Serverless API
Qwen Image is available via sciforium' serverless API, where you pay per token. Use the REST API or OpenAI-compatible client libraries to generate images.
DocsSeed-Based Reproducibility
Pass a seed parameter to get deterministic outputs — the same prompt and seed will produce the same image every time.
DocsMiniMax M2.5
Kimi K2.5
GLM 5
DeepSeek V3.2
gpt-oss-120b
gpt-oss-20b
Qwen3 Instruct
Qwen3 Thinking
Qwen3 Coder
Qwen3.5
Qwen3 VL Instruct
Qwen3 ASR
Qwen-Image
Qwen-Image-Edit
Flux2
Stable Diffusion 3.5
Hunyuan Image
Z-Image
Wan2.2-I2V
Wan2.2-T2V
Hunyuan Image
Z-Image