待验证50% 置信事实精确时间
Doubao's image generation capabilities are based on ByteDance's SDXL fine-tuned model and a proprietary image generation engine.
1
来源数
50%
置信度
中期 (~90 天)
时效性
2026/7/2
首次发现
有效期至：2026/9/30
来源
5 AI Image-to-Prompt Tools Tested and Compared: Which One Works Best?
bilibili数字丛林2026/6/8
相关事实
待验证Doubao is an AI tool developed by ByteDance that can both reverse-engineer image prompts and generate images from them.76% 相似待验证豆包是字节跳动旗下的AI工具，背后依托字节跳动自研的云雀大模型（Doubao模型），其图像生成能力基于字节的SDXL微调模型和自研的图像生成引擎68% 相似待验证Tools like Doubao and Wenxin Yiyan use models similar to Stable Video Diffusion or proprietary video generation models for image-to-video generation.65% 相似待验证Doubao（豆包）具备多模态能力，可以生成图像和视频，并且完全免费64% 相似待验证SD3、FLUX及Qwen-Image-3.0等主流大型图像生成模型普遍转向LLM文本编码器与DiT图像骨干融合的架构64% 相似
引用此条事实
Stable URI
https://kongchang.com/claim/43041API
curl https://kongchang.com/api/v1/knowledge/claims/43041MCP
get_claim(id=43041)