Add vision model for volcengine

[deific]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

Volcengine already has a multimodal model that supports image recognition: Doubao-vision-pro 32k. This model is not included in the model list of dify's volcengine model provider. When it is introduced in a custom way, the vision control switch cannot be turned on.

2. Additional context or comments

No response

3. Can you help us with this feature?

• I am interested in contributing to this feature.

[eye8]

I also need to access Doubao-vision-pro 32k in Dify. Please support! Thank you.

[zhangever]

Expecting