makecindy / makecindy/cindy

Cindy AI 图片生成不可用:seedance 未接入图片通道,仅 openai 需额外key

Open
#2,422 2 comments 0 reactions 0 assignees View on GitHub
feature
Dominant language
TypeScript
Stars
2.7k
Forks
395
Avg merge
21h 48m
Merged PRs (30d)
776

Description

**提交人**: 彭乙峰
**客户端版本**: 0.1.44

---

## 补充发现:Seedance 未接入图片生成

模型供应商描述/Seedance 产品本身支持图片生成(字节 Seedance 是多模态生成模型),但 Cindy 集成中:
- Art 插件 `gen_video`/`edit_video` 支持 seedance(视频生成)✅
- Art 插件 `gen_image`(文生图)只支持 `openai/gpt-image-2`,seedance 被拒 ❌
- 模型目录 model-catalog/model-pricing 中无 seedance 图片条目 ❌
- host 无 `image_generate` 内置工具暴露给 agent ❌

## 期望
请将 seedance 接入图片生成通道(gen_image 支持 seedance / 或提供 image_generate 内置工具),让 Cindy AI 套餐(xd 供应商)能直接生图,无需 OpenAI API key。

## 现状背景
- 图片生成目前仅 openai/gpt-image-2 可用,需 OpenAI Platform API key(用户不愿额外付费)
- 视频生成走 seedance 已可用(xd 供应商)
- 期望两者统一到 Cindy AI 套餐覆盖范围内
---
**版本区域**: CN
**OS**: win32 x64 (10.0.19045)
**界面语言**: zh-CN

Contributor guide

Open the contributing guide

Research direction

Start by tracing the Art plugin's gen_image path and compare it with gen_video's seedance support. Then inspect model-catalog/model-pricing and the host's built-in tools to determine how image generation is registered. Done means seedance is accepted for image generation through the Cindy AI package without requiring an OpenAI key, with the relevant catalog and agent exposure updated.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
ai
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.