制作角色立绘与角色设定图
截至 2026-10-09，AI 把这项工作做到 L2 部分自动化。9 条更新涉及它，最强的证据：仅来自发布方。
- 级别
- L2部分自动化
- 更新
- 9
- 公司
- 5Google · Alibaba · MiniMax
- 最强证据
- T3仅来自发布方
是什么把它推到这里
涉及这项工作的全部更新，最新的在前。
- 2026-10-06GoogleNano Banana 2.1 now available in Google Flow
Google Flow adds Nano Banana 2.1 with improved visual quality and subject consistency for generation and editing. Nano Banana Pro and Nano Banana 2 Lite remain available.
- 2026-10-06GoogleGoogle launches Nano Banana 2.1 image generation and editing model
Google released Nano Banana 2.1, an upgraded image generation and editing model with improvements in visual design, mask-based editing, and subject consistency.
- 2026-09-20AlibabaQwen-Image-2.1 image generation model released with open weights
Alibaba's Qwen team released Qwen-Image-2.1, a unified image generation and editing model, with open weights. It gained day-0 support in vLLM and ComfyUI.
- 2026-09-17AlibabaQwen available in n8n via Gateway credits
From n8n v2.36, Cloud Starter and Pro users can call Qwen through Gateway credits for text, image, and video generation in a single node, without an API key or separate account.
- 2026-09-11MiniMaxMiniMax Design major upgrade with GPT-6 Astra, MCP integrations, collaborative projects
MiniMax Design received a major upgrade adding GPT-6 Astra, new MCP integrations for Blender, PS, AE and more, and Collaborative Projects for teamwork.
- 2026-09-10GoogleGoogle launches Pics image generation and editing tool
Google introduces Pics, built with Nano Banana, for generating, refining and co-creating images with object isolation and text editing capabilities.
- 2026-09-08OpenAIOpenAI introduces GPT-Image-2.5 Flare and Sunburst in the API
OpenAI adds new image models, GPT-Image-2.5 Flare and Sunburst, to its API with sharper detail, stronger style adherence, and more edit control.
- 2026-09-08OpenAIOpenAI releases ChatGPT Images 2.5
OpenAI launches ChatGPT Images 2.5 with faster generation, improved fidelity, consistent details across edits, and comment-based editing tools.
- 2026-08-24Moonshot AIKimi-K3 goes live with 2.8T parameters and 1M-token context
Kimi-K3 is live with 2.8T parameters and native 1M-token context, aimed at repo-scale engineering, visual creation and planning agents; a 1M-token free trial is available on Model Studio and Qwen Cloud.