大模型不支持文生图，图生图等模型

**Describe the bug**

{
"$error": "Workflow execution failure: Error code: 500 - {\"code\":\"InternalServiceError\",\"message\":\"The service encountered an unexpected internal error. Request id: 0217608043821904239eeb08f794b3419181d9d62341b39add103\",\"param\":\"\",\"type\":\"InternalServerError\",\"request_id\":\"2025101816194200000FBD512448FFCE5B\"}"
}
A clear and concise description of what the bug is.

**To Reproduce**

Steps to reproduce the behavior:

**Expected behavior**

A clear and concise description of what you expected to happen.

**Screenshots**

If applicable, add screenshots to help explain your problem.

**Version:**

Please provide the version of {project_name} you are using.

**Environment:**

The output of `go env`.

**Additional context**

Add any other context about the problem here.
我的配置如下：
`id: 60000
name: Doubao Seedream 4.0
icon_uri: default_icon/doubao_v2.png
icon_url: ""
description:
zh: 图生图 文生图Seedream 4.0
en: doubao model description Seedream 4.0
default_parameters:
- name: temperature
label:
zh: 生成随机性
en: Temperature
desc:
zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
type: float
min: "0"
max: "1"
default_val:
balance: "0.8"
creative: "1"
default_val: "1.0"
precise: "0.3"
precision: 1
options: []
style:
widget: slider
label:
zh: 生成多样性
en: Generation diversity
- name: max_tokens
label:
zh: 最大回复长度
en: Response max length
desc:
zh: 控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。
en: You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.
type: int
min: "1"
max: "4096"
default_val:
default_val: "4096"
options: []
style:
widget: slider
label:
zh: 输入及输出设置
en: Input and output settings
- name: top_p
label:
zh: Top P
en: Top P
desc:
zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
type: float
min: "0"
max: "1"
default_val:
default_val: "0.7"
precision: 2
options: []
style:
widget: slider
label:
zh: 生成多样性
en: Generation diversity
- name: response_format
label:
zh: 输出格式
en: Response format
desc:
zh: '- **文本**: 使用普通文本格式回复\n- **Markdown**: 将引导模型使用Markdown格式输出回复\n- **JSON**: 将引导模型使用JSON格式输出'
en: '**Response Format**:\n\n- **Text**: Replies in plain text format\n- **Markdown**: Uses Markdown format for replies\n- **JSON**: Uses JSON format for replies'
type: int
min: ""
max: ""
default_val:
default_val: "0"
options:
- label: Text
value: "0"
- label: Markdown
value: "1"
- label: JSON
value: "2"
style:
widget: radio_buttons
label:
zh: 输入及输出设置
en: Input and output settings
meta:
protocol: ark
capability:
function_call: true
input_modal:
- text
- image
input_tokens: 128000
json_mode: false
max_tokens: 128000
output_modal:
- text
output_tokens: 16384
prefix_caching: false
reasoning: false
prefill_response: false
conn_config:
base_url: "https://ark.cn-beijing.volces.com/api/v3/"
api_key: "41bc7803-6165-4ee5-84e0-2af1d036b2"
timeout: 120s
model: "doubao-seedream-4-0-250828"
temperature: 0.1
frequency_penalty: 0
presence_penalty: 0
max_tokens: 4096
top_p: 0.7
top_k: 0
stop: []
enable_base64_url: false
ark:
region: ""
access_key: ""
secret_key: ""
retry_times: null
custom_header: {}
status: 0
`

Start by reproducing the workflow with the supplied Doubao Seedream 4.0 configuration and inspect the model capability and Ark connection settings involved in the failure. Determine whether the reported 500 error is caused by unsupported text-to-image or image-to-image handling, then verify that the supported modalities execute without the internal-service failure.

Written by the indexing model from the issue text.