Alibaba 模型
Alibaba Wan, Qwen-Image and Z-Image via API: text-to-image, image editing, inpainting and ControlNet-guided image generation models.
Alibaba Group develops the Wan, Qwen-Image and Z-Image text-to-image and image editing models through Tongyi Lab, which builds Wan and Z-Image, and the Qwen team, which builds Qwen-Image. The company was founded in Hangzhou, China, in 1999 by 18 people led by Jack Ma, and is still headquartered there.
可用模型
找到 5 个模型系列
Z-Image
alibaba/z-image-base/text-to-image文生图$0.01 / 百万像素
alibaba/z-image-turbo/text-to-image文生图$0.005 / 百万像素
alibaba/z-image-turbo/image-to-image图生图$0.005 / 百万像素
alibaba/z-image-turbo-controlnet/image-to-image图生图$0.0065 / 百万像素
alibaba/z-image-turbo-inpaint/image-to-image图生图$0.01 / 百万像素
alibaba/z-image-turbo-tiling/text-to-image文生图$0.02 / 百万像素
Wan 2.7
alibaba/wan-2.7/text-to-image文生图$0.03 / 张
alibaba/wan-2.7/image-to-image图生图$0.03 / 张
alibaba/wan-2.7-pro/text-to-image文生图$0.075 / 张
alibaba/wan-2.7-pro/image-to-image图生图$0.075 / 张
2 个能力
alibaba/wan-2.5-preview/text-to-image文生图$0.05 / 张
alibaba/wan-2.5-preview/image-to-image图生图$0.05 / 张
Wan 2.2
alibaba/wan-2.2-5b/text-to-image文生图$0.016 / 张
alibaba/wan-2.2-a14b/text-to-image文生图$0.025 / 张
1 个能力
alibaba/qwen-image/text-to-image文生图$0.02 / 百万像素
关于厂商
Alibaba builds language, image and video models and publishes many of them with open weights. Its image models cover text-to-image generation, instruction-based image editing, inpainting and rendering text inside images.
- Wan: Text-to-image and image editing from Tongyi Lab's Wan line, which also covers video; Wan 2.2 has Apache 2.0 weights and its A14B model uses mixture-of-experts.
- Qwen-Image: Text-to-image on a 20B-parameter MMDiT model from the Qwen team; renders complex text in images, including multi-line English and Chinese.
- Z-Image: Text-to-image on 6B-parameter open-weight models; Base for fine-tuning, Turbo for 8-step generation, and Turbo variants for ControlNet, inpainting and tiling.
通过 API 接入
一把 MuseSpan API 密钥即可调用本页所有 Alibaba 模型：复制模型 ID，填进请求的 model 字段。