太nb了，一句话，吃了个饭，生成了一部 ai 短剧，然后 agent 拿推特上来给我发了。这真的要把那些拍线下实体的干倒闭了。
《月陨剑庭》第1集：她被仙门处死三年后，竟从禁地活着回来了
后面还有 9 集，脚本已经写好，让他每天根据数据优化下。
中文
Bruce Guai
558 posts
Bruce Guai
@BruceGuai
Vibe Marketer ｜ Head of Marketing @flowith Digital Researcher @UCLBartlett
Los Angeles, CA Katılım Temmuz 2024
383 Takip Edilen3K Takipçiler
当下最强的生图 Agent 上线flowith，在细节、联网、优化生图质量上有非常大的提升，用户可以自定义选择图片模型。
这里也是 seedance2.0➕gpt image 2组合的最佳平台
转赞评原贴可以获得更多积分⬇️！
Flowith@flowith
the most powerful image agent has arrived. flowith image agent doesn’t just make better images. It builds perfect visual workflows. - zoom-worthy details - text that actually works - search-aware creative intelligence - images to videos with seedance 2.0 from one prompt to a complete campaign workflow. like, comment, and retweet for 20 random membership drops!
中文
🚨 breaking deepseek v4 is here
Whale finally back
while GPT 5.5 is here today who is the best?
English
Bullish on open-source!
Kimi.ai@Kimi_Moonshot
We're open-sourcing FlashKDA — our high-performance CUTLASS-based implementation of Kimi Delta Attention kernels. Achieves 1.72×–2.22× prefill speedup over the flash-linear-attention baseline on H20, and works as a drop-in backend for flash-linear-attention. Explore on github: github.com/MoonshotAI/Fla…
English
Breaking 🚨 the best tool for using gpt image 2 is here
gpt-image-2 is on @flowith
90% off 🎁
Flowith@flowith
the era of scrambled ai typography is officially over. we used gpt-image-2 to create this wsj-styled front page reporting tim cook stepping down as apple ceo. every headline, every column, every single dot, all generated in one prompt . coming soon on flowith.
English
can't believe these are ai generated.... just in one line
GPT-image2 = the claude 3.5 moment for image models==
English
English
Introducing Canvas Cowork.
an open-sourced creative workflow for Claude Code, Codex, OpenClaw, and other agents.
More people are using coding agents for creative work now.
The problem: the current interface is not built for it.
Long context breaks. Branches get messy.
Images, video, text, and agent outputs end up scattered across linear threads and hacked-together tools.
Flowith Canvas Cowork skill fixes that with a shared visual canvas: your agents can now access node-based context, batch generation, multimodal workflows. It’s real collaboration between you and your agents.
No server. No API key mess.
Just connect and create.
Open source: github.com/flowith-ai/can…
English
