I've got some good news for you! "TheStarflow AI Agent, https://www.xingliu.art/" is now officially online!
Just say what you want, whether you want pictures, videos, or design programs, it can handle it all! If you feel dissatisfied after doing it, directly say where to change, it instantly understands and adjusts to your satisfaction in minutes!
It is worth mentioning that its in-depth Chinese attributes are very suitable for our oriental aesthetics, and it is a treasure choice for domestic designers! Not only can you understand the key points of the demand, but also understand the details of the aesthetic, which is a reliable AI design partner!
At this stage, both the web and app versions are available, so no matter where you are, you can let it work for you at any time! Mom no longer needs to worry about me catching the last train to get off work!
You make the requirements, it comes up with the design! Star Stream Agent: True - Chinese AI design artifact, free to use today!
LiblibAI's king bomb "Starflow Agent" is here! 🎯 It is a direct copy of Lovart's all-around design gene, and also specially upgraded the Chinese environment:
✅ Knowing Chinese and aesthetics, the double buff is strong!
✅Super understanding of the heart of our domestic designers!
✅ It does what it says it will do: you ask for a requirement and it comes up with a complete design for you straight away!
Benefit Time! 3 free experiences per day! Don't hesitate to try it! Tell StarStream Agent your ideas and see how it "transforms" you into amazing pictures, videos, and programs. Supported by all platforms, you can use it as soon as you have internet access, and realize your inspiration in seconds!
Common tasks for e-commerce designers: quickly generate e-commerce promotion posters.
Cue word:Help me generate 3 e-commerce mask posters, each image shows an orange and white gradient mask, mainly to show the shooting of this mask product, the image has both the product box and bag packaging, the product stands on the table, the table is covered with white silk, there is a little bit of fuzzy flowers behind the product, the background is a light orange-pink-purple gradient sunset sky, the overall style of the overall tonality of the light pink Orange, the picture is rich in content, super texture, super real texture, super quality, big brand texture tonality, large white space, centered composition, 4K.
Just set the direction, and StarStream Agent turns into a "requirement disassembler"! It automatically generates design blueprints, and arranges the details of scale, composition, color scheme, and typography for you! Next, it will also intelligently call kontext and other professional engines to realize accurate drawing!
Voila, six Estee Lauder Brown Bottle posters on the canvas in no time! The style can change, but the core need is not compromised:
Need an "AI Design Sense"? The main structure is solid! "Product information" "Bottle text"? Key details are all preserved and never sloppy! This is a solid process of "Requirements → Blueprint → Draft", and even if it is generated by AI, you can step on the requirements without going off on a tangent!
Web: Poster Modification
Poster modification
Intelligent Modification
Take the first poster, click on the image and the smart editing toolchain is immediately activated - HD zoom in, expand, remove background, erase - all of these functions instantly wake up!
Want to erase text? Use the "Pixel Erase Function" to get rid of it with precision! The AI processed edges are so clean that you can't see a single trace of it.
This is a testament to LiblibAI's technological prowess in the field of AIGC tools!
Web: ASMR style video
ASMR video
Cue word:Making five videos with Video3, a surreal 4K macro slow-motion close-up captures a dramatic scene: a hand wielding a hammer that smashes into a burning charcoal keyboard in one powerful blow. Each key is made of incandescent charcoal that burns with ash and immediately cracks, sending out sparks, ash and glistening fragments. The impact produces a plume of smoke and searing embers, and the surface emits a fiery pulse. Audio features sharp popping, hissing charcoal breaks accompanied by the crackling of burning embers. Warm flickering orange-red lights highlight the intense flame damage and flying sparks. The sound is ASMR style.
Web: ASMR style video
ASMR video
Cue word:Making five videos with Video3, a surreal 4K macro slow-motion close-up captures a dramatic scene: a hand wielding a hammer that smashes into a burning charcoal keyboard in one powerful blow. Each key is made of incandescent charcoal that burns with ash and immediately cracks, sending out sparks, ash and glistening fragments. The impact produces a plume of smoke and searing embers, and the surface emits a fiery pulse. Audio features sharp popping, hissing charcoal breaks accompanied by the crackling of burning embers. Warm flickering orange-red lights highlight the intense flame damage and flying sparks. The sound is ASMR style.
Web: ASMR style video
ASMR video
Cue word:Making five videos with Video3, a surreal 4K macro slow-motion close-up captures a dramatic scene: a hand wielding a hammer that smashes into a burning charcoal keyboard in one powerful blow. Each key is made of incandescent charcoal that burns with ash and immediately cracks, sending out sparks, ash and glistening fragments. The impact produces a plume of smoke and searing embers, and the surface emits a fiery pulse. Audio features sharp popping, hissing charcoal breaks accompanied by the crackling of burning embers. Warm flickering orange-red lights highlight the intense flame damage and flying sparks. The sound is ASMR style.
Web: ASMR style video
ASMR video
Cue word:Making five videos with Video3, a surreal 4K macro slow-motion close-up captures a dramatic scene: a hand wielding a hammer that smashes into a burning charcoal keyboard in one powerful blow. Each key is made of incandescent charcoal that burns with ash and immediately cracks, sending out sparks, ash and glistening fragments. The impact produces a plume of smoke and searing embers, and the surface emits a fiery pulse. Audio features sharp popping, hissing charcoal breaks accompanied by the crackling of burning embers. Warm flickering orange-red lights highlight the intense flame damage and flying sparks. The sound is ASMR style.
Web: Chinese Poster
Summary and Review
Father's Day Poster
Cue word:Father's Day poster design in a 3D, super cute style, with a father pulling his child around in a circle in a grassy field, with an impactful elevation angle to the image. The background is a long, clean, lush meadow, with the grass blowing in the wind and white clouds floating in the grass, rich in storytelling and artistry, with an imaginative color scheme of highly saturated blues and greens. The grass reads "Father's Day" in casual three-dimensional lettering.
Web: Chinese Poster
Summary and Review
Father's Day Poster
Cue word:Father's Day poster design in a 3D, super cute style, with a father pulling his child around in a circle in a grassy field, with an impactful elevation angle to the image. The background is a long, clean, lush meadow, with the grass blowing in the wind and white clouds floating in the grass, rich in storytelling and artistry, with an imaginative color scheme of highly saturated blues and greens. The grass reads "Father's Day" in casual three-dimensional lettering.
24 Seasons Poster
Solar term poster
Cue word:Help me generate 6 Chinese festival posters with a unified style, where the festival date and title are displayed.
As the official Chinese version of Lovart, Starstream Agent's Chinese language ability is significantly enhanced. I asked it to design 6 poster festive posters for itself with a unified style, and it gave free rein to design 6 posters with the same style. Overall.As the Chinese version of Lovart, StarStream Agent is still powerful, less expensive and more convenient to use, and it is the first choice of designer Agent in China.
Whether you're a professional designer or a casual user with no design knowledge at all, if you have an idea, you can count on Agent to take care of the rest.
09
Web-side: operation flow
Operation method
StarStream Agent is definitely the AI partner of choice for domestic designers! It doesn't matter if you're a bigwig or a novice designer, as long as you have an idea in your head, just say it, and it will take care of the rest of the tedious, energy-consuming work -- it's reliable as can be!
From photo retouching to complete brand design, from APP interface to cool 3D videos, Starstream Agent directly crushes the threshold of design! What used to be a time-consuming task is now "just a mouthful", saving time and effort! Want to let your creativity fly? Want to make your visual effects unique? With Agent, it's like you've suddenly gained design superpowers, and you'll be amazed by the whole audience in minutes!
Today I'm sharing a super fast-actingUpward Tracks
--AI Facial beauty hot dance video.
This is one of my hands-on accounts:
Just getting started posting videos like this not too long ago.
Basically, all the bars are popping, with thousands and thousands of likes.
It goes without saying that the uptick is even more so!
Today I'm sharing a super fast-actingUpward Tracks
--AI Facial beauty hot dance video.
This is one of my hands-on accounts:
Just getting started posting videos like this not too long ago.
Basically, all the bars are popping, with thousands and thousands of likes.
It goes without saying that the uptick is even more so!
Find a couple other models:Contrast female big series, F1-Small red book photo _ the strongest sense of the net
2 Generate Image Let's go back to the Starstream AI and find the joined model, here the base model we'll pick:ethereal and dreamy (idiom); unrealistic and unimaginable
Once the models are all loaded, we'll go below theEnter a prompt in the prompt box
Then modify the settings.The size of the image and the number of generated sheets are 4, and then point to the raw chart.
It is possible to generate a few more, thePick the ones that work well and right click to download them.
3Video ProductionLet's open it.Korin AI, to generate graphic videos.
Upload our previous image, write the cue word underneath it, add the reverse cue word in the patch, choose 1.6 for the model, time 5 seconds high quality
Recently TikTok, Xiaohongshu, youtube, set off a wave of "AI cut fruit ASMR" video craze: A knife fell gently, and the crystal strawberries snapped and shattered with the crisp sound of breaking glass, relaxing the mind and body for a few seconds, theMillions of views, comments begging for the "original video."The
How exactly are these types of videos made? Which AI tool is used? Is it complicated? Is there a fee?
Today's post.Hands-on with Google Veo 3 Free ProductionThese kinds of videos, zero cost, zero editing basics, just do it 👇 (however, open the Veo 3 (Link requires point magic configuration)
✅ Step 1: Prepare the Prompt (Prompt)
The core of the generated video is text alertIt's like giving instructions to an AI:
"What kind of scene are you shooting, what objects are there, what shots, what sounds"
Don't make up your own cue words, the best way for newbies to do it:Copy, then change, then write.The
🧠 Example prompt word 1 (good for getting started quickly):
Realistic 4K footage close up of a knife rapidly cutting a glowing purple glass peach on a wooden cutting board. Each slice falls apart with a crisp ASMR- style glass shatter sound. style glass shatter sound.
👉 You just need to change "purple glass peach" to the desired fruit, e.g. glass mango / apple / lemon...
🧠 Example Prompt Word 2 (Premium + Multiple Perspectives):
Shot in extreme macro, a flawless, crystal-clear [fruit] rests on a wooden board under warm light. The knife slices it slowly with a clean " ting" sound. Reflections shimmer on the surface, ASMR-style audio layers blend gently in a quiet environment.
👉 [fruit] Replace the object you want to make, e.g. glass watermelon / diamond pineapple etc.
🔄 Quickly generate prompt words (AI help writing recommended):
Let DeepSeek / ChatGPT mimic these structures and make a template where one line of input outputs an entire prompt, for example:
Input: blue glass lemon Output: a whole paragraph of ve o cue words
✅ Step 2: Generate Video with Veo 3
Veo is Google's latest Text to Video ToolIt has support for 1080P + ASMR sound + multi-angle shooting.
📍 Method 1: Gemini official website (easy to use)
Link: https://gemini.google.com
Using the Gemini 2.5 Pro model
Enter the prompt
Click on the video button → wait for generation
📍 Method 2: Google Labs Flow (customizable)
Link: https://labs.google/flow/
Switch model to: Veo 3 - Fast (Text to Video)
Simultaneous generation of 1~4 videos with continuous frames and transitions
More flexible point consumption and more parameters
🎬 Final advice: don't just play, make accounts!
The ASMR fruit-cutting video isn't a "toy," it's a Traffic Codes + Content ModelsThe
You can make these kinds of videos like the TikTok pop-up bloggers doBatch Generation, Periodic Release, made into an exclusive account.
It is also possible to take the realization path:
Packaging your generation experience, editing process → doing paid tutorials
Cradle It is an open-source program by the BAAI-Agents team for General Computer Control (GCC) s multimodal AI Agent framework, which allows large multimodal models to use a variety of software and games like a human via screenshot input and keystroke output.
Common goal: support for any native software (e.g. games, Office, image/video editing tools)
Multi-modal input: screenshot as input, support keyboard and mouse operation as output
Modular design: high controllability and scalability, easy to adapt to new environments
pain point scenario
Since the birth of the GPT series of gurus, LLMs have seen explosive growth. However, they rely on "API text input/output", which makes them unable to control the local interface, and local task automation is still difficult:
Operation of Office, visualization software is limited
Splitting complex tasks makes it difficult to close the loop
Lack of visual ability to locate UI elements based on language alone
Inability to memorize history for long periods of time and insufficient execution of multi-step logic
Cradle is designed to address these pain points:
Controls mouse and keyboard to simulate human operation
Strengthening "self-reflection" and "skill optimization" strategies
Supports long-range tasks, complex gaming environments, and specialized software operations
core functionality
Below is a list of Cradle's 6 core module features:
Information Gathering
Processing UI screenshots, text messages using visual models
Audio feedback can be accessed to complete the interoceptive input
Self-Reflection
Review historical operational results to determine if they were achieved
Summarize the reasons for failure and provide guidance for the next run
Task Inference
Inferring current goals based on environment + historical memory
Dynamic Programming Next Optimal Policy
Skill Curation
Generate or update skill functions for each task
Customized strategies by environment for experience
Action Planning
LLM outputs high-level actions (e.g., "click on X" "move mouse to Y")
Translation of human-written bridging layers to keystrokes and mouse actions
Memory module (Memory)
Short-term and long-term memory, including historical records
Supports reuse of memories and skills across tasks
These modules form a set of closed loops: input screenshot → what you see → introspection → planning → execution → memory feedback.
Experiments have proven that Cradle can be accomplished:
AAA Games:Red Dead Redemption 2 Main quests, high success rate completion;
Municipal Games:Cities: Skylines Creating a City of a Thousand;
Farm Games:Stardew Valley Automatic seeding and harvesting;
Business Game:Dealer's Life 2 Achieve the highest weekly profit of 87%;
Office software: Sign in to Chrome, reply to Outlook, use Feishu;
Does not rely on internal UI interfaces and adapts to a wide range of software.
Highly modular configuration
Easily scalable to new games or software environments
Progressive capacity enhancement
LLM + self-reflection + memory techniques to support self-improvement
Universal Operating Interface
Screenshots + Keyboard and Mouse Output, Truly Universal
An illustration of the interface
application scenario
R&D AI Agent can autonomously simulate user actions, replacing UI API testing https://wxa.wxs.qq.com/tmpl/mi/base_tmpl.html
Office automation: a large number of repetitive tasks (emails, forms, reports) can be completely automated.
Game AI development: Become an in-game intelligence, test missions/train NPCs
Process Automation: Provides UI automation pipeline with less reliance on traditional RPA
Education and Training: Cradle demonstrates how to do things and helps students understand complex software.
Who's stronger?
Framework project
Support Mode
Whether or not it relies on an API
Key requirements
Core Advantages
Cradle
Screenshots + Keyboarding
❌ No API
Complete closed-loop, self-directed learning
Versatility, Modularity, Wide Adaptation
LangChain Agent
Text API Input/Output
✅ With API
Text commands / HTTP requests
Expertise in information retrieval, text management
AutoHotkey / RPA etc.
keyboard and mouse macro (computing)
❌ No API
Single-step macro operation, lack of memory planning
Easy to use but low intelligence, weak self-improvement
Playwright/Selenium
DOM Manipulation API
✅ DOM API
web automation
Specializes in web, more limited than desktop
Strengths: Cradle is a multimodal, cognitively-enabled "universal software executable" that goes beyond traditional or web automation tools.
Article Summary
Cradle is the first general-purpose software-controlled AI agent.Supports a wide range of local software and AAA game operations.
The core is 6 modules with self-thinking, self-learning, and self-adaptive capabilities.
Modularized and maintainable technical architecture
Compared to traditional tools, Cradle offers a video-quality experience, global closed-loop intelligence, and the ability to create a new, more efficient, and more effective way of communicating with your customers.
Suitable for R&D automation, office, game development and teaching scenarios.
Hello, everyone, I'm Li Hua, an AI blogger with over 100,000 followers across the web, specializing in AI science and intelligent body sharing.
Recently I've been working on an intelligent body workflow for generating a series of short self-publishing videos with Coze, with the goal of generating a variety of explosive short videos with a single click.
Today we're going to share the Immersive Historical Storytelling Video Intelligence Body workflow, and we'll start with a case study.
This jitterbug account @strange history Only 56 entries, surprisingly up 480,000 fans, all of which are explosive.
After a few days of research, I finally got the logic and flow of it sorted out and developed the workflow.
All I had to do was enter a history-based topic in the workflow run box, click on the trial run, and soon a short pop-up history video was generated for me in one click.
For example, I typed in "darkness", clicked run, generated a short video draft, and then exported the draft in Cutting and Screening, and the following video was created.
Seeing how the demo works, how was this workflow created?
I. Development of ideas:
Generate copy topics, backgrounds, and image cues based on themes via big models
Mirror pictures based on cued word derivatives
Determination of the screen presentation through the image generation and drawing board module
Generate a timeline from the audio and create a draft cutscene
III. Detailed workflow analysis
1. Start node
2、Generate short video copy according to the theme
3, with the help of large model students into the mirror prompt words
4, batch processing to generate images, audio
5. Create a draft cutout and generate a corresponding timeline based on the audio
At this point, the workflow for immersive historical storytelling is developed.
Thank you for reading, if this article is helpful to you, please like to pay attention to Oh, I will continue to share good workflow tutorials.
This tool has been placed in our shared space, and there are dozens of smart body workflows for you to experience~!
Welcome to my AI Intelligentsia workspace!
You will acquire the rights and benefits:
Dozens of intelligent workflows are at your disposal when you enter the co-creation space, and more will be added all the time!
〇 Exclusive member group Q&A service, any questions in the use of intelligent body workflow can be
　　　　Members and friends can mention the needs of the body, the demand for more will be developed to put space for everyone to use!
English 
Chinese 
Japanese 
German 
