[{"data":1,"prerenderedAt":381},["ShallowReactive",2],{"$fgukOamtKU1RtUiMFsqdObttmqPPQz0uc7bl_gj_LyX0":3,"$fEoKEphfbU0HA7f9bdnd6bQbfz2e_a8sy56DWgNprtW0":245,"article-327":380},{"code":4,"msg":5,"data":6},0,"",{"category":7,"tag":11,"popular":19,"latest":86,"banner":126,"list":151,"cache":244},[8,9,10],"Agent","OpenAI","LLM",[8,12,13,14,9,10,15,16,17,18],"Google","Nvidia","Claude","DeepSeek","OCR","Chat","Generator",[20,29,37,45,54,62,70,79],{"id":21,"publish_date":22,"is_original":23,"collection":5,"cover_url":24,"cover_url_1_1":25,"title":26,"summary":27,"author":28},411,"2023-09-10",1,"article_res/cover/451ef50c225a8dc61c4336506794d13b.jpeg","article_res/cover/3ba9dc7a72f87d40b20fc2d225289ee3.jpeg","Idealism","Reality is created by the mind, we can change our reality by changing our mind. - Plato","Renee's Entrepreneurial Journey",{"id":30,"publish_date":31,"is_original":23,"collection":32,"cover_url":33,"cover_url_1_1":34,"title":35,"summary":36,"author":28},108,"2024-12-07","#LLM #AGI #AI Agent","article_res/cover/0039044422e4ec9f61c18e8ee1693bb0.jpeg","article_res/cover/4220971b108a91d21407d87bb02fbaa6.jpeg","Freysa.ai: The World's First Adversarial AI Agent Game","说服 Freysa 把钱包里的钱都拿出来",{"id":38,"publish_date":39,"is_original":23,"collection":40,"cover_url":41,"cover_url_1_1":42,"title":43,"summary":44,"author":28},12,"2025-03-09","#Oxford #Reasoning #LLM #Tool Use","article_res/cover/d448e9b3617a0b5302e1bd10c438bca9.jpeg","article_res/cover/864a468f9cc4c9317efadb3811909888.jpeg","Agentic Reasoning Framework - Significantly enhance the reasoning ability of LLMs through the integration of external tools using agents","Agentic Reasoning: Reasoning LLMs with Tools for Deep Research",{"id":46,"publish_date":47,"is_original":4,"collection":48,"cover_url":49,"cover_url_1_1":50,"title":51,"summary":52,"author":53},480,"2023-04-14","#Stable Diffusion","article_res/cover/0bdbe7cb1de4a78e54536e5d9afa7ec9.jpeg","article_res/cover/b3d6ffec0608dcfaf18c5a69906d1490.jpeg","【AIGC Learning】Generate Prompts Using Word Graphs - Stable Diffusion Web UI Series 13","AI will become a powerful tool in education, transforming the way we learn and deliver instruction.  \n- Reid Hoffman","--",{"id":55,"publish_date":56,"is_original":4,"collection":57,"cover_url":58,"cover_url_1_1":59,"title":60,"summary":61,"author":28},413,"2023-09-08","#Neuroscience","article_res/cover/74f8302d78a23d9430f22171eae136b6.jpeg","article_res/cover/87ca08af81bb304746be5261160964c0.jpeg","Can machines be conscious?","Do we have an ethical obligation to not turn off conscious machines? Would turning them off be murder? No. I don't lose any sleep over unplugging a conscious machine.\n- Jeff Hawkins, \"A Thousand Brains\"",{"id":63,"publish_date":64,"is_original":23,"collection":65,"cover_url":66,"cover_url_1_1":67,"title":68,"summary":69,"author":28},178,"2024-09-09","#Entrepreneurship","article_res/cover/a7224f025b55d1820408085faef63079.jpeg","article_res/cover/11a9995b096cbf64465ef01b8673b154.jpeg","37signals company","This damn sense of relaxation",{"id":71,"publish_date":72,"is_original":4,"collection":73,"cover_url":74,"cover_url_1_1":75,"title":76,"summary":77,"author":78},460,"2023-05-12","#Google","article_res/cover/b970687b12faa52da976f91248c2aa7b.jpeg","article_res/cover/d1e71b52cfd2c63bc6e71f3e85ff135c.jpeg","Learn what BRC-20 and Ordinals are using Google Bard","Ordinals - a new protocol that allows users to store arbitrary data on the Bitcoin blockchain","Google Bard mainly writes",{"id":80,"publish_date":81,"is_original":23,"collection":5,"cover_url":82,"cover_url_1_1":83,"title":84,"summary":85,"author":28},309,"2024-03-26","article_res/cover/9877f95894ee88532d0e6012c23a2df3.jpeg","article_res/cover/20092164ddc109ce6ae56b1984246751.jpeg","Learning the Cancun Upgrade with lepton and perplexity","Building a quick conversation-based search demo with Lepton AI.",[87,95,103,111,119],{"id":88,"publish_date":89,"is_original":23,"collection":90,"cover_url":91,"cover_url_1_1":92,"title":93,"summary":94,"author":28},627,"2025-03-20","#AI Avatar #AI Video Generation","article_res/cover/d95481358f73924989f8c4ee9c75d1c8.jpeg","article_res/cover/b74bc0fab01f8b6a6aa87696c0c3ed8b.jpeg","DisPose: Generating Animated Videos by Driving Video with Reference Images","DisPose is a controllable human image animation method that enhances video generation.",{"id":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},626,"2025-03-21","#Deep Dive into LLMs #LLM #RL #Andrej Karpathy #AlphaGo","article_res/cover/446553a5c8f8f2f07d97b20eaee84e56.jpeg","article_res/cover/e6c2823409c9b34624064b9acbaca6f1.jpeg","AlphaGo and the Power of Reinforcement Learning - Andrej Karpathy's Deep Dive on LLMs (Part 9)","Simply learning from humans will never surpass human capabilities.",{"id":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},625,"2025-03-22","#Deep Dive into LLMs #LLM #RL #RLHF #Andrej Karpathy","article_res/cover/8da81d38b1e5cf558a164710fd8a5389.jpeg","article_res/cover/96f028d76c362a99a0dd56389e8f7a9b.jpeg","Reinforcement Learning from Human Feedback (RLHF) - Andrej Karpathy's Deep Dive on LLMs (Part 10)","Fine-Tuning Language Models from Human Preferences",{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},624,"2025-03-23","#Deep Dive into LLMs #LLM #Andrej Karpathy #AI Agent #MMM","article_res/cover/a5e7c3d48bb09109684d6513287c661d.jpeg","article_res/cover/d3f22b7c0ab8d82fd2da457a299e0773.jpeg","The Future of Large Language Models - Andrej Karpathy's In-Depth Explanation of LLM (Part 11)","preview of things to come",{"id":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},623,"#Google #Voe #AI Video Generation","article_res/cover/c44062fea0f336c2b96b3928292392c2.jpeg","article_res/cover/a041041c69092ad3db191c5bf3ff981b.jpeg","Trial of Google's video generation model VOE2","Our state-of-the-art video generation model",[127,135,143],{"id":128,"publish_date":129,"is_original":23,"collection":130,"cover_url":131,"cover_url_1_1":132,"title":133,"summary":134,"author":28},300,"2024-04-16","#AI in Science #AGI","article_res/cover/6bf01e793e0f33e848572412eebdf9b0.jpeg","article_res/cover/91a5ee21dafecb914fabeb9430d46ec1.jpeg","Would Einstein lose his job - AI and Quantum Computing: A Glimpse into the Near Future","So Einstein's job is still safe.",{"id":136,"publish_date":137,"is_original":23,"collection":138,"cover_url":139,"cover_url_1_1":140,"title":141,"summary":142,"author":28},101,"2024-12-14","#Nvidia #AI 3D Generator","article_res/cover/693e07c85980c5c0c8fde3f037733f23.jpeg","article_res/cover/9ea8edff2d5d303ff3fffff3f6f9c3d9.jpeg","NVIDIA's open-source 3D project LLaMA-Mesh","LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models",{"id":144,"publish_date":145,"is_original":23,"collection":146,"cover_url":147,"cover_url_1_1":148,"title":149,"summary":150,"author":28},131,"2024-11-10","#OpenAI","article_res/cover/87f8ed353ce39f31960e7cdfaf075a35.jpeg","article_res/cover/f597a63935f5cd32e484b4aadd6019e8.jpeg","ChatGPT has launched the Search function","Get fast, timely answers with links to relevant web sources.",{"big":152,"small":214},[153,181],{"title":154,"list":155},"AGENT",[156,157,165,173],{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":158,"publish_date":159,"is_original":23,"collection":160,"cover_url":161,"cover_url_1_1":162,"title":163,"summary":164,"author":28},622,"2025-03-24","#OWL #AI Agent #MAS #MCP #CUA","article_res/cover/cb50ca7f2bf4d1ed50202d7406e1c19a.jpeg","article_res/cover/4aa7aa3badfacf3cc84121334f1050dd.jpeg","OWL: Multi-agent collaboration","OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation",{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},620,"2025-03-26","#LLM #Google #Gemini #AI Agent","article_res/cover/53751a6dbbe990b1eb0b63f3b062aed4.jpeg","article_res/cover/031344981f0a212ff82d1f3a64aa5756.jpeg","Gemini 2.5 Pro, claimed to be far ahead of the competition, has been released with great fanfare: comprehensively surpassing other LLMs and topping the global rankings","Gemini 2.5: Our most intelligent AI model",{"id":174,"publish_date":175,"is_original":23,"collection":176,"cover_url":177,"cover_url_1_1":178,"title":179,"summary":180,"author":28},616,"2025-03-29","#MAS #AI Agent #AI Coder #MetaGPT #MGX","article_res/cover/9dcd702ad2035902e5e77967c34a1f1e.jpeg","article_res/cover/0a97fc4a922753c8f46ff38792020df8.jpeg","MGX - An automated website-building platform composed of multiple AI Agents","Your 24/7 AI Team | Dream, Chat, Create.",{"title":182,"list":183},"OPENAI",[184,191,199,206],{"id":185,"publish_date":167,"is_original":23,"collection":186,"cover_url":187,"cover_url_1_1":188,"title":189,"summary":190,"author":28},619,"#OpenAI #AI Image Generator #4o #MMM #AR Transformer","article_res/cover/2faffc97fcecf3151552cb0fd3206d89.jpeg","article_res/cover/1133cb4948af44cee2e7fbe79efb69e5.jpeg","The native image function of GPT-4o is officially launched","Introducing 4o Image Generation",{"id":192,"publish_date":193,"is_original":4,"collection":194,"cover_url":195,"cover_url_1_1":196,"title":197,"summary":198,"author":28},434,"2023-07-15","#Anthropic #OpenAI #Google #AI Code Generator #Claude","article_res/cover/e1b6f600a2b9f262a4392684e5f2ce25.jpeg","article_res/cover/6e1772e83f78f9a351ab23d3e414adee.jpeg","Latest Updates on Google Bard /Anthropic Claude2 / ChatGPT Code Interpreter","We want our models to use their programming skills to provide more natural interfaces to the basic functions of our computers.  \n - OpenAI",{"id":200,"publish_date":201,"is_original":4,"collection":146,"cover_url":202,"cover_url_1_1":203,"title":204,"summary":205,"author":28},417,"2023-08-24","article_res/cover/bccf897d50a88b18364e35f7466387e0.jpeg","article_res/cover/2f871085c1073717c1703ae86e18056f.jpeg","The GPT-3.5 Turbo fine-tuning (fine-tuning function) has been released～","Developers can now bring their own data to customize GPT-3.5 Turbo for their use cases.",{"id":207,"publish_date":208,"is_original":4,"collection":209,"cover_url":210,"cover_url_1_1":211,"title":212,"summary":213,"author":28},407,"2023-09-22","#OpenAI #AI Image Generator","article_res/cover/c59005e903d35cfc32346e2756e2728a.jpeg","article_res/cover/ba011d265e6d84b5c8cb6fd6b757b6cc.jpeg","Dall-E 3","DALL·E 3 understands significantly more nuance and detail, allowing you to easily translate your ideas into images.",[215,221,241],{"title":10,"list":216},[217,218,219,220],{"id":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},{"id":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"title":222,"list":223},"GOOGLE",[224,225,226,234],{"id":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"id":227,"publish_date":228,"is_original":23,"collection":229,"cover_url":230,"cover_url_1_1":231,"title":232,"summary":233,"author":28},615,"2025-03-30","#AI Researcher #AI Science #HKU #Google #AI Agent","article_res/cover/21fadf906067714bb0db31ae13a77c15.jpeg","article_res/cover/2697999a72bd26b22e85f0e92936d3ed.jpeg","AI-Researcher: LLM-driven全自动 scientific research assistant","AI-Researcher: Fully-Automated Scientific Discovery with LLM Agents  \nOpen-Sourced Alternative to Google AI Co-Scientist",{"id":235,"publish_date":236,"is_original":23,"collection":73,"cover_url":237,"cover_url_1_1":238,"title":239,"summary":240,"author":28},463,"2023-05-09","article_res/cover/89800f207723acdb55fc53bf999ebdc9.jpeg","article_res/cover/5764f369b4accd8f83e94aa4c077a175.jpeg","The Smallville sandbox world - A town with 25 virtual residents","Believable proxies of human behavior can empower interactive apps: Immersive environment, Rehearsal space, Prototyping tool",{"title":242,"list":243},"NVIDIA",[],true,{"code":4,"msg":5,"data":246},{"id":247,"publish_date":248,"is_original":23,"collection":5,"articles_id":249,"cover_url":250,"cover_url_1_1":251,"title":252,"summary":253,"author":28,"content":254,"popular":255,"list":320,"category":378,"tag":379},327,"2024-02-20","equ5jnlxGxPTq93YDxz9Mw","article_res/cover/d49a37da85f7e9382f7ad372e45d78ed.jpeg","article_res/cover/62b0323c9403a7915fb6c0f70ee6a55b.jpeg","StableCascade: A Faster and Better Open-Source Image Generation Model","The smaller the latent space, the faster you can run inference and the cheaper the training becomes.","\u003Cdiv class=\"rich_media_content js_underline_content\n                       autoTypeSetting24psection\n            \" id=\"js_content\">\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Today I checked out StableCascade, released by Stability AI (one of the companies behind Stable Diffusion). Both the speed and quality of their image generation are exceptional.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003662\" data-ratio=\"0.5416666666666666\" data-s=\"300,640\" data-type=\"jpeg\" data-w=\"1080\" style=\"\" src=\"./assets/17423811126780.9824106109762814.jpeg\">\u003C/p>\u003Cul data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">The latest version of ComfyUI already supports these features.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003664\" data-ratio=\"0.3476190476190476\" data-s=\"300,640\" data-type=\"png\" data-w=\"630\" style=\"\" src=\"./assets/17423811126560.777641986591294.png\">\u003C/p>\u003Cp>\u003Cbr>\u003C/p>\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">Just update ComfyUI to the latest version and download the corresponding few models, and you can run the workflow.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003663\" data-ratio=\"0.7324074074074074\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423811127300.6848154467062124.png\">\u003C/p>\u003Cp>\u003Cbr>\u003C/p>\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">You can use this demo's workflow to experience their high-speed and high-quality performance. https://gist.github.com/comfyanonymous/0f09119a342d0dd825bb2d99d19b781c\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003667\" data-ratio=\"0.4824074074074074\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423811127200.0062886794308820715.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003666\" data-ratio=\"0.6037037037037037\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423811126640.7455681151340499.png\">\u003C/p>\u003Cp>\u003Cbr>\u003C/p>\u003C/section>\u003C/li>\u003C/ul>\u003Ch3 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 20px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>Model Introduction\u003C/h3>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>This model is built on the Würstchen architecture, and its main difference from Stable Diffusion lies in that it operates in a smaller latent space, allowing for faster inference and lower training costs.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003670\" data-ratio=\"0.4\" data-s=\"300,640\" data-type=\"jpeg\" data-w=\"1080\" style=\"\" src=\"./assets/17423811127540.9435042586503344.jpeg\">\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Stable Diffusion uses a compression factor of 8, resulting in 1024x1024 images being encoded as 128x128. Stable Cascade achieves a compression factor of 42, meaning that 1024x1024 images can be encoded as 24x24 while maintaining clear reconstruction quality. Then, a text-conditioned model is trained in this highly compressed latent space. A previous version of this architecture achieved a 16x cost reduction compared to Stable Diffusion 1.5. Stable Cascade has achieved impressive results both visually and in evaluations, performing best in prompt alignment and aesthetic quality in almost all comparisons.\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>All known extensions, such as fine-tuning, LoRA, ControlNet, IP-Adapter, LCM, etc., can also be implemented using this method. Some of these (fine-tuning, ControlNet, LoRA) have already been provided for training and inference. Currently, ComfyUI does not support these extensions, but support should come soon.\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>ControlNet\u003C/span>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003672\" data-ratio=\"1.3037214885954382\" data-s=\"300,640\" data-type=\"png\" data-w=\"833\" style=\"\" src=\"./assets/17423811153770.5987233792626716.png\">\u003C/p>\u003Cp>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>LoRA\u003C/span>\u003C/span>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003673\" data-ratio=\"0.6079346557759626\" data-s=\"300,640\" data-type=\"png\" data-w=\"857\" style=\"\" src=\"./assets/17423811128710.9471620854444616.png\">\u003C/p>\u003Ch3 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 20px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>Model Overview\u003C/h3>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Stable Cascade consists of three models: Stage A, Stage B, and Stage C, representing the cascading process of generating images, hence the name \"Stable Cascade.\" Stages A and B are used for image compression, similar to the role of VAE in Stable Diffusion. However, as mentioned earlier, this setup allows for a higher degree of image compression. Additionally, Stage C is responsible for generating a small 24 x 24 latent space based on textual prompts. The following figure intuitively illustrates this process. Note that Stage A is a VAE, while Stages B and C are both diffusion models.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003671\" data-ratio=\"0.637962962962963\" data-s=\"300,640\" data-type=\"jpeg\" data-w=\"1080\" style=\"\" src=\"./assets/17423811127570.4435944777617997.jpeg\">\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>For this release, StabilityAI provides two checkpoints for stage C, two for stage B, and one for stage A. Stage C has a 1 billion parameter version and a 3.6 billion parameter version, but the official recommendation is to use the 3.6 billion parameter version as most of the work has been focused on its fine-tuning. The two versions of stage B have 700 million and 1.5 billion parameters respectively. Both can achieve excellent results, but the 1.5 billion parameter version performs better in reconstructing small details. Therefore, using the larger variant at each stage will yield the best results. Finally, stage A contains 20 million parameters and remains fixed due to its smaller scale.\u003C/p>\u003Ch3 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 20px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>Comparison\u003C/h3>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Stable Cascade (30 inference steps) was compared with Playground v2 (50 inference steps), SDXL (50 inference steps), SDXL Turbo (1 inference step), and Würstchen v2 (30 inference steps).\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003669\" data-ratio=\"0.5127314814814815\" data-s=\"300,640\" data-type=\"png\" data-w=\"864\" style=\"\" src=\"./assets/17423811138430.4189023863494914.png\">\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Stable Cascade's focus on efficiency is reflected in its architecture and more compressed latent space. Despite the largest model having 1.4 billion more parameters than Stable Diffusion XL, it still offers faster inference times.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003668\" data-ratio=\"0.6425925925925926\" data-s=\"300,640\" data-type=\"jpeg\" data-w=\"1080\" style=\"\" src=\"./assets/17423811147280.2846147797987879.jpeg\">\u003C/p>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",[256,265,272,280,288,297,305,312],{"id":257,"title_md5":258,"publish_date":259,"author_md5":260,"is_original":4,"collection":261,"summary_md5":262,"cover_url":263,"cover_url_1_1":264},473,"3189486fc6f498f1b5504f379191b9ac","2023-04-21","bc27fa490c4d0d525bac812fc0793534","#Prompt Engineering #Langchain","eb05bf22b71e4fe9541b51f033ddd418","article_res/cover/6feff73eb419c10d4231db31be4b1369.jpeg","article_res/cover/32309b6df502a7cf63048e0313e9be86.jpeg",{"id":266,"title_md5":267,"publish_date":268,"author_md5":260,"is_original":23,"collection":146,"summary_md5":269,"cover_url":270,"cover_url_1_1":271},274,"ec0fe99770562eb8158a92552f1c1bab","2024-05-14","12d6643202a9ece809df243a978e0f94","article_res/cover/c5ee2cc9c65b9afc3f7a3a42680c91eb.jpeg","article_res/cover/e477f861806e7092392a2c02142cb5e0.jpeg",{"id":273,"title_md5":274,"publish_date":275,"author_md5":260,"is_original":23,"collection":276,"summary_md5":277,"cover_url":278,"cover_url_1_1":279},203,"2c408d886a6f7344e88f7b1de0d5fd86","2024-08-06","#AI 3D Generator","85c753f4be6c3938c4a4916d348142ab","article_res/cover/68382532dcde38141c8b44efe285413d.jpeg","article_res/cover/4028f0d69e23efa6431ffcfeea9e65a3.jpeg",{"id":281,"title_md5":282,"publish_date":283,"author_md5":284,"is_original":4,"collection":5,"summary_md5":285,"cover_url":286,"cover_url_1_1":287},513,"4bd18446d477b97bd0c1d848b0bc355e","2022-06-24","8b3607d0f4181a3cb6ffdccf7185f09b","51980e3c4fe120760b1b37c7d42cc1c8","article_res/cover/7f38c4c22e1e55447a7082cf3b2127b1.jpeg","article_res/cover/98f91218af4907c5811e91490f822ec2.jpeg",{"id":289,"title_md5":290,"publish_date":291,"author_md5":292,"is_original":4,"collection":293,"summary_md5":294,"cover_url":295,"cover_url_1_1":296},497,"d378cba4a702060a27a68164fd31f012","2023-02-03","cfab1ba8c67c7c838db98d666f02a132","#Entrepreneurship #Psychology","188d1ecc87be52ec0bdde50c4f0970c7","article_res/cover/fc13cb4a40d5006b6ab96baf922a8cf0.jpeg","article_res/cover/d8d80c64874011e73ef9502a3f9f99f6.jpeg",{"id":298,"title_md5":299,"publish_date":300,"author_md5":260,"is_original":23,"collection":301,"summary_md5":302,"cover_url":303,"cover_url_1_1":304},48,"ceddd3a0051768a5d39d487af4ef8b7d","2025-02-05","#AI Agent #AI Avatar #Alibaba #AI Video Generator","29ca4273479e890a427f18a993572631","article_res/cover/b4b09d99258fcd5045abbea17c3ad843.jpeg","article_res/cover/7d789b6343a2bdb2c8748571d9440ef1.jpeg",{"id":306,"title_md5":307,"publish_date":268,"author_md5":260,"is_original":4,"collection":308,"summary_md5":309,"cover_url":310,"cover_url_1_1":311},275,"15751a77f7da4bcba33eff3ff5a0811a","#LLM","cbfe16f9ef04dc79ba98a5cb2c23959b","article_res/cover/3ebae852d0132307cb13b9b68ead6b83.jpeg","article_res/cover/1675fc145cc31c6bdb0f404a3e7ae098.jpeg",{"id":313,"title_md5":314,"publish_date":315,"author_md5":260,"is_original":23,"collection":316,"summary_md5":317,"cover_url":318,"cover_url_1_1":319},96,"2606299aa85b82a155dcf95efdfb7847","2024-12-19","#OpenAI #LLM #ChatGPT","3bccabb72efefc849d584040de6806ec","article_res/cover/5ade9b60d58aa520d9a28561c64d8c5d.jpeg","article_res/cover/ddfa142e8b7f1e655226194a9bddf230.jpeg",{"related":321,"small":363},[322,331,339,347,355],{"id":323,"publish_date":324,"is_original":4,"collection":325,"cover_url":326,"cover_url_1_1":327,"title":328,"summary":329,"author":330},601,"2022-03-16","#Psychology","article_res/cover/ea61315067c2244c9727afe4bdf9a11b.jpeg","article_res/cover/17c29fb73778c34dabe6b5148aa4321d.jpeg","Raw egg and boiled egg","When we feel fragile, we’re like raw eggs; when we develop more resilience, we’re like hard-boiled eggs","Psychological counseling notes",{"id":332,"publish_date":333,"is_original":23,"collection":334,"cover_url":335,"cover_url_1_1":336,"title":337,"summary":338,"author":28},224,"2024-07-09","#AI Avatar","article_res/cover/670fbb56c51f582e4b359a0b5c9eefd0.jpeg","article_res/cover/c9a84424a4c803f0e2565e847e9f36ac.jpeg","Kuaishou's LivePortrait - A Video-driven Avatar Animation Framework","LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control",{"id":340,"publish_date":341,"is_original":23,"collection":342,"cover_url":343,"cover_url_1_1":344,"title":345,"summary":346,"author":28},138,"2024-10-31","#State of AI Report 2024 #Nvidia","article_res/cover/75ecb7ee1a8464bd0d1289b6ee3c16af.jpeg","article_res/cover/9b168a16002d3be5868c95188dd309c2.jpeg","\"State of AI Report 2024\" (final) - 10 predictions for the next 12 months","10 predictions for the next 12 months",{"id":348,"publish_date":349,"is_original":4,"collection":65,"cover_url":350,"cover_url_1_1":351,"title":352,"summary":353,"author":354},545,"2022-05-11","article_res/cover/d73e286a65a482df39f4e9a80f0a55b1.jpeg","article_res/cover/0695fd87a23b3e413a5a4d97e60fe3f6.jpeg","Brother Cong and Brother Qi's Anthology","If people are like duckweed, we have no choice in the kind of era or world we live in. But we can choose what to revere, embrace, and never give up on in our hearts. No matter how out of place or absurd this persistence may temporarily seem, and no matter how weak and vulnerable those ideals from a bygone era may appear in the eye of the storm in a dark world.","Entrepreneurial Insights",{"id":356,"publish_date":357,"is_original":4,"collection":5,"cover_url":358,"cover_url_1_1":359,"title":360,"summary":361,"author":362},576,"2022-04-10","article_res/cover/ab33f7df918c9b6b0c02f57f839c1726.jpeg","article_res/cover/8ac9ee6a467d13ac8504aa7f9631a302.jpeg","My Perspective on Love","Every gift has a price","Chit-chat",[364,370,376],{"title":10,"list":365},[366,367,368,369],{"id":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},{"id":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"title":222,"list":371},[372,373,374,375],{"id":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"id":227,"publish_date":228,"is_original":23,"collection":229,"cover_url":230,"cover_url_1_1":231,"title":232,"summary":233,"author":28},{"id":235,"publish_date":236,"is_original":23,"collection":73,"cover_url":237,"cover_url_1_1":238,"title":239,"summary":240,"author":28},{"title":242,"list":377},[],[8,9,10],[8,12,13,14,9,10,15,16,17,18],["Reactive",245],1754646421683]