This model generates beautiful cinematic 2 megapixel images in 3-4 seconds and is derived from the Wan 2.2 model through optimisation techniques from the pruna package
prunaai/wan-2.2-image
来源检查时间: 2026-09-13 · 供应商端点记录，不代表独立效果评测。
以下是来源观察记录，不能直接相互替代。Token、计算耗时、输出时长与按次价格不能仅比较数值；输入和可选功能可能另行计费。
| 来源标价 | 计费单位 | 条件 | 依据 |
|---|---|---|---|
| $0.02 USD | output image | or 50 images for $1 | 公开结构化来源 |
| aspect_ratio | Aspect ratio for the generated image · Options: 1:1, 16:9, 9:16, 4:3, 3:4, 21:9 · Default: 16:9 |
|---|---|
| output_format | Format of the output images · Options: png, jpg, webp · Default: jpg |
| output_quality | Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs · Min: 1 · Max: 100 · Default: 80 |
未列出的参数、地区可用性、最低充值、税费和商用条款仍待核实，购买前请核对精确端点。
Fast、Pro、编辑和音频版本保持独立。比较费用前，请确认版本与配置一致。
来源目录中的端点和计价条件。不同端点不等于不同基础模型；账号报价不参与最低价排名。
以下是已采集接口数，不等于独立模型数，也不代表平台已全部采完。价格依据包含数值和来源计价说明。尚无已发布接口的平台仍待采集。
4 个端点 · 1/1
不同规格单独列出。打开模型查看计费单位与适用条件。
Replicate · 图片
图片模型prunaai/wan-2.2-imageThis model generates beautiful cinematic 2 megapixel images in 3-4 seconds and is derived from the Wan 2.2 model through optimisation techniques from the pruna package
wavespeed-ai/wan-2.2/image-to-imageWAN 2.2 (14B) is an image-to-image model for high-resolution photorealistic image editing with exceptional precision and fidelity. Ready-to-use REST inference API, best performance, no coldstarts, aff
wavespeed-ai/wan-2.2/text-to-image-loraWAN 2.2 generates super-detailed images from text prompts and supports custom LoRAs for fine-grained style and subject control. Ready-to-use REST inference API, best performance, no coldstarts, afford
wavespeed-ai/wan-2.2/text-to-image-realismWAN 2.2 delivers ultra-realistic text-to-image generation, converting prompts into photoreal images with high fidelity and detail. Ready-to-use REST inference API, best performance, no coldstarts, aff