[{"data":1,"prerenderedAt":205},["ShallowReactive",2],{"DlFXI4Eibt_Bn9lrEZz1TYbHCWFZj3IvqwHQSEW-Exc":3,"pW3tYsLJi88VIeCC3JxL8phBfjb0AxoJQER0JGezHvU":194},{"code":4,"msg":5,"data":6},0,"",{"category":7,"tag":11,"hot":39,"new":78,"banner":118,"data":143,"cache":193},[8,9,10],"Agent","OpenAI","LLM",[12,14,17,20,23,25,27,30,33,36],{"title":8,"total":13},39,{"title":15,"total":16},"Google",44,{"title":18,"total":19},"Nvidia",13,{"title":21,"total":22},"Claude",11,{"title":9,"total":24},35,{"title":10,"total":26},85,{"title":28,"total":29},"DeepSeek",9,{"title":31,"total":32},"OCR",1,{"title":34,"total":35},"Chat",7,{"title":37,"total":38},"Generator",116,[40,48,55,64,71],{"id":41,"publish_date":42,"is_original":4,"collection":5,"cover_url":43,"cover_url_1_1":44,"title":45,"summary":46,"author":47},557,"2022-04-29","article_res/cover/7a9b1375ed9bb298154981bae42b794d.jpeg","article_res/cover/afa281dd52bc0454e6735daa8e6b0706.jpeg","Translation and summary of Messari Report [2.8 Kristin Smith, Blockchain Association and Katie Haun, a16z]","We need unity and speed right now.","Translation",{"id":49,"publish_date":50,"is_original":4,"collection":5,"cover_url":51,"cover_url_1_1":52,"title":53,"summary":54,"author":47},531,"2022-05-25","article_res/cover/e8362057f8fa189594c60afdfaaeb6e5.jpeg","article_res/cover/8ea08d0d6fa7eee6b57ed4ec61b61ad6.jpeg","Decentralized Society: Finding Web3’s Soul / Decentralized Society: Finding the Soul of Web3 -7","Decentralization through Pluralism When analyzing ecosystems, it's desirable to measure how decentralized it is.",{"id":56,"publish_date":57,"is_original":32,"collection":58,"cover_url":59,"cover_url_1_1":60,"title":61,"summary":62,"author":63},127,"2024-11-14","#Google #AI Game #World Model #AI Story","article_res/cover/0233a875b7ec2debf59779e311547569.jpeg","article_res/cover/6ffddb6ae4914b3c699493311aa9f198.jpeg","Google Launches \"Unbounded\": A Generative Infinite Character Life Simulation Game","Unbounded: A Generative Infinite Game of Character Life Simulation","Renee's Entrepreneurial Journey",{"id":13,"publish_date":65,"is_original":32,"collection":66,"cover_url":67,"cover_url_1_1":68,"title":69,"summary":70,"author":63},"2025-02-14","#Deep Dive into LLMs #Andrej Karpathy #LLM #Tool Use #Hallucination","article_res/cover/11e858ad6b74dfa80f923d549b62855c.jpeg","article_res/cover/615e1b320f1fc163edc1d2d154a6de33.jpeg","Andrej Karpathy's in-depth explanation of LLM (Part 4): Hallucinations","hallucinations, tool use, knowledge/working memory",{"id":72,"publish_date":73,"is_original":4,"collection":5,"cover_url":74,"cover_url_1_1":75,"title":76,"summary":77,"author":47},579,"2022-04-07","article_res/cover/39387376ba28447af1eb40576b9df215.jpeg","article_res/cover/02727ede8551ed49901d0abe6d6305b7.jpeg","Messari Report Translation and Summary 【1-7 Surviving the Winter】","I’d be more cautious here: 10 year and 10 hour thinking only.",[79,87,95,103,111],{"id":80,"publish_date":81,"is_original":32,"collection":82,"cover_url":83,"cover_url_1_1":84,"title":85,"summary":86,"author":63},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":88,"publish_date":89,"is_original":32,"collection":90,"cover_url":91,"cover_url_1_1":92,"title":93,"summary":94,"author":63},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":96,"publish_date":97,"is_original":32,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":63},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":104,"publish_date":105,"is_original":32,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":63},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":112,"publish_date":105,"is_original":32,"collection":113,"cover_url":114,"cover_url_1_1":115,"title":116,"summary":117,"author":63},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",[119,127,135],{"id":120,"publish_date":121,"is_original":32,"collection":122,"cover_url":123,"cover_url_1_1":124,"title":125,"summary":126,"author":63},160,"2024-10-04","#Philosophy","article_res/cover/496990c49211e8b7f996b7d39c18168e.jpeg","article_res/cover/14dbaa1ade9cb4316d5829423a900362.jpeg","Time","The fungus of the morning does not know the waxing and waning of the moon, and the cicada does not know the seasons; this is a short life. To the south of the state of Chu there is a dark spirit which regards five hundred years as spring and five hundred years as autumn. In ancient times there was a great tree called the Ming which regarded eight thousand years as spring and eight thousand years as autumn; this is a long life.",{"id":128,"publish_date":129,"is_original":32,"collection":130,"cover_url":131,"cover_url_1_1":132,"title":133,"summary":134,"author":63},98,"2024-12-17","#AI Video Generator #Sora #Pika","article_res/cover/3b86e85d03fff4f356a3e4cf2bb329c9.jpeg","article_res/cover/5fa5c20ad0b40f8f544d257c0ef02938.jpeg","Pika 2.0 video generation officially released: effect comparison with Sora","今天，我们推出了Pika 2.0模型。卓越的文字对齐效果。惊人的视觉表现。还有✨场景成分✨",{"id":136,"publish_date":137,"is_original":32,"collection":138,"cover_url":139,"cover_url_1_1":140,"title":141,"summary":142,"author":63},71,"2025-01-14","#Nvidia #World Foundation Model #Cosmos #Physical AI #Embodied AI","article_res/cover/feddf8c832dfb45d28804291f6a42a9e.jpeg","article_res/cover/d6bc2f1186d96b78228c2283a17a3645.jpeg","NVIDIA's Cosmos World Model","Cosmos World Foundation Model Platform for Physical AI",[144,163,188],{"title":8,"items":145},[146,147,155],{"id":104,"publish_date":105,"is_original":32,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":63},{"id":148,"publish_date":149,"is_original":32,"collection":150,"cover_url":151,"cover_url_1_1":152,"title":153,"summary":154,"author":63},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":156,"publish_date":157,"is_original":32,"collection":158,"cover_url":159,"cover_url_1_1":160,"title":161,"summary":162,"author":63},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",{"title":9,"items":164},[165,172,180],{"id":166,"publish_date":157,"is_original":32,"collection":167,"cover_url":168,"cover_url_1_1":169,"title":170,"summary":171,"author":63},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":173,"publish_date":174,"is_original":4,"collection":175,"cover_url":176,"cover_url_1_1":177,"title":178,"summary":179,"author":63},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":181,"publish_date":182,"is_original":4,"collection":183,"cover_url":184,"cover_url_1_1":185,"title":186,"summary":187,"author":63},417,"2023-08-24","#OpenAI","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.",{"title":10,"items":189},[190,191,192],{"id":88,"publish_date":89,"is_original":32,"collection":90,"cover_url":91,"cover_url_1_1":92,"title":93,"summary":94,"author":63},{"id":96,"publish_date":97,"is_original":32,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":63},{"id":104,"publish_date":105,"is_original":32,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":63},true,{"code":4,"msg":5,"data":195},{"id":196,"publish_date":197,"is_original":32,"collection":198,"articles_id":199,"cover_url":200,"cover_url_1_1":201,"title":202,"summary":203,"author":63,"content":204},344,"2024-01-12","#Object Detection #AI Image Generator #LLM","MDrXAtEG51I6T3iscGdL-Q","article_res/cover/5de43be205fd639aa478da130187b2a6.jpeg","article_res/cover/c95bdda03e7b7643d4f3fafa1387bfa2.jpeg","Two papers from UC Berkeley: Exploring LLM-enhanced diffusion models for text-to-image translation","Text Prompt -> LLM -> Intermediate Representation (such as an image layout) -> Stable Diffusion -> Image.","\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 read two papers with similar content, both focusing on how to use Large Language Models (LLMs) to control Diffusion Models.\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;'>Both papers were published by UC Berkeley: \"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models\" and \"Self-correcting LLM-controlled Diffusion Models\", which were released in May and November of last year respectively.\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;'>The URLs for the related projects are as follows:\u003C/p>\u003Cul class=\"list-paddingleft-1\" style=\"list-style-type: disc;\">\u003Cli>\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;'>https://llm-grounded-diffusion.github.io\u003C/p>\u003C/li>\u003Cli>\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;'>https://self-correcting-llm-diffusion.github.io\u003C/p>\u003C/li>\u003C/ul>\u003Chr style=\"border-style: solid;border-width: 1px 0 0;border-color: rgba(0,0,0,0.1);-webkit-transform-origin: 0 0;-webkit-transform: scale(1, 0.5);transform-origin: 0 0;transform: scale(1, 0.5);\">\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;'>\u003Cbr>\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;'>\u003Cstrong>Let's first look at the first paper: \"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models\".\u003C/strong>\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;'>: Text Prompt -> Large Language Model (LLM) -> Intermediate Representation (e.g., image layout) -> Stable Diffusion -> Image\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003358\" data-ratio=\"1.2010178117048347\" data-s=\"300,640\" data-type=\"png\" data-w=\"393\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812110400.018094719301475992.png\">\u003C/p>\u003Cp>\u003Cbr>\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;'>Diffusion models still face challenges in handling complex prompts, especially those involving numerical calculations and spatial reasoning. This study proposes a method to enhance the prompt understanding ability of diffusion models - LMD.\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;'>The LMD method leverages a pre-trained large language model (LLM), achieving grounded generation in a novel two-stage process:\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003359\" data-ratio=\"0.2369727047146402\" data-s=\"300,640\" data-type=\"png\" data-w=\"806\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812109230.03740457674008013.png\">\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);\">, the LLM generates a scene layout based on the given prompt description, which includes captioned bounding boxes that describe the desired image.\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">, a novel controller guides an off-the-shelf diffusion model for layout-based image generation.\u003C/section>\u003C/li>\u003C/ul>\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;'>Both stages use existing pre-trained models without requiring additional model parameter optimization.\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;'>\u003Cbr>\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;'>LMD naturally enables:\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003360\" data-ratio=\"0.39092055485498106\" data-s=\"300,640\" data-type=\"png\" data-w=\"793\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812110390.9909110494259519.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;'>a. Performing multi-round scene specification based on instructions;\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;'>b. Generating images from prompts in languages not supported by the base diffusion model.\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;'>\u003Cstrong>\u003Cbr>\u003C/strong>\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;'>\u003Cstrong>Comparison\u003C/strong>\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;'>The LMD method significantly outperforms the base diffusion model and several strong baselines in accurately generating images described by prompts requiring various capabilities, doubling the generation accuracy on average across four tasks.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003364\" data-ratio=\"0.5237556561085973\" data-s=\"300,640\" data-type=\"png\" data-w=\"884\" src=\"https://res.cooltool.vip/article_res/assets/17423812112630.8457397378799203.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003366\" data-ratio=\"0.27282976324689967\" data-s=\"300,640\" data-type=\"png\" data-w=\"887\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812123760.43447061104176865.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003367\" data-ratio=\"0.6324074074074074\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812125090.4155423734044865.png\">\u003C/p>\u003Chr style=\"border-style: solid;border-width: 1px 0 0;border-color: rgba(0,0,0,0.1);-webkit-transform-origin: 0 0;-webkit-transform: scale(1, 0.5);transform-origin: 0 0;transform: scale(1, 0.5);\">\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;'>\u003Cbr>\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;'>\u003Cstrong>The second article \"Self-correcting LLM-controlled Diffusion Models\"\u003C/strong>\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;'>: Existing diffusion-based text-to-image generators (e.g., DALL-E 3) often struggle to precisely generate images fully aligned with complex input prompts, especially those requiring numerical calculations and spatial relationships.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003368\" data-ratio=\"0.32314814814814813\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812112770.42067667449489954.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;'>The SLD framework enables these diffusion models to automatically and iteratively correct inaccuracies by applying a series of latent space operations (addition, deletion, repositioning, etc.), thereby achieving better text-to-image alignment.\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;'>Features of the SLD framework include:\u003C/p>\u003Col 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);\">Self-correction: Enhancing the generative model through an integrated LLM detector to achieve precise text-to-image alignment.\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Unified generation and editing: Performs excellently in both image generation and fine-grained editing.\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Universal compatibility: Applicable to any image generator, such as DALL-E 3, without requiring additional training or data.\u003C/section>\u003C/li>\u003C/ol>\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;'>SLD enhances text-to-image alignment through an iterative self-correction process. It starts with object detection driven by LLMs, followed by LLM-controlled analysis and correction.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003369\" data-ratio=\"0.6240740740740741\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812129540.3306249568509889.png\">\u003C/p>\u003Cp>\u003Cbr>\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;'>The latent operations of SLD can be summarized into two key concepts:\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003370\" data-ratio=\"0.7686676427525623\" data-s=\"300,640\" data-type=\"png\" data-w=\"683\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812341040.7724374548759974.png\">\u003C/p>\u003Col 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);\">The latent representation of removed areas is re-initialized as Gaussian noise, while the latent representation of newly added or modified objects is synthesized onto the canvas.\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Latent synthesis is limited to the initial steps, followed by the \"unfreezing\" step of the standard forward diffusion process, which enhances visual quality and avoids artificial copy-paste effects.\u003C/section>\u003C/li>\u003C/ol>\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;'>\u003Cbr>\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;'>By leveraging the advanced localization capabilities of the OWL-ViT v2 open vocabulary detector, we can accurately identify all seagulls in the image, enabling selective removal to meet user prompt requirements. As shown in the following figure:\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003376\" data-ratio=\"0.41944847605224966\" data-s=\"300,640\" data-type=\"png\" data-w=\"689\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812165010.8195517038544473.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;'>\u003Cbr>\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;'>SLD improves the text-to-image alignment accuracy of various diffusion-based generative models including SDXL, LMD+, and DALL-E 3. As shown in the following figure, as indicated by the red box in the first row, SLD precisely locates the blue bicycle associated with the bench and palm tree, while maintaining the accurate number of palm trees and seagulls. The second row further demonstrates the robustness of SLD in complex, cluttered scenes, effectively managing object collisions through latent operations without training.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003371\" data-ratio=\"0.4601851851851852\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812123930.08871989831380378.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;'>\u003Cbr>\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;'>SLD can handle a variety of image editing tasks guided by natural, human-like instructions. Its capabilities cover a wide range, from adjusting the number of objects to changing object attributes, positions, and sizes. As shown in the following figure\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003373\" data-ratio=\"0.4981481481481482\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812131520.4994228189336347.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;'>\u003Cstrong>Comparison\u003C/strong>\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;'>It shows significantly better performance in executing these object-level edits.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003372\" data-ratio=\"0.6575342465753424\" data-s=\"300,640\" data-type=\"png\" data-w=\"657\" src=\"https://res.cooltool.vip/article_res/assets/17423812122070.7535429540357106.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003374\" data-ratio=\"0.6785714285714286\" data-s=\"300,640\" data-type=\"png\" data-w=\"700\" src=\"https://res.cooltool.vip/article_res/assets/17423812165030.08988734757897432.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003375\" data-ratio=\"0.6438547486033519\" data-s=\"300,640\" data-type=\"png\" data-w=\"716\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423812122660.044655636054125925.png\">\u003C/p>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",1752585433437]