Following the free language model GLM-4-Flash in August.Zhipu AI went live today with the first freeMultimodal Model —— GLM-4V-FlashThe GLM-4V-Flash not only builds on the excellent capabilities of the 4V series models, but also achieves improved accuracy in image processing.
The GLM-4V-Flash model is described as having aImage description generation, image classification, visual inference, visual question and answer (VQA), and image sentiment analysisIt supports advanced image processing functions and 26 languages including Chinese, English, Japanese, Korean, and German.
In enterprise applications, GLM-4V-Flash can provide precise scene solutions for specific vertical industries, helping developers quickly integrate into the era of large models at low cost, without worrying about the high cost of large model image processing.
1AI attaches the relevant links below:
- Experience Center: https://www.bigmodel.cn/console/trialcenter
- Instruction document: https://www.bigmodel.cn/dev/api/normal-model/glm-4v