[{"data":1,"prerenderedAt":823},["ShallowReactive",2],{"blog-vision-models-claude-chatgpt-llava":3,"surround-vision-models-claude-chatgpt-llava":775,"i-tabler:menu-2":784,"i-tabler:chevron-down":789,"i-tabler:rocket":791,"i-tabler:arrow-left":793,"i-tabler:arrow-right":795,"i-tabler:brand-discord":797,"i-tabler:brand-x":799,"i-tabler:brand-youtube":801,"i-tabler:brand-linkedin":803,"i-tabler:brand-facebook":805,"i-tabler:brand-instagram":807,"i-tabler:brand-tiktok":809,"i-tabler:user":811,"i-tabler:building":813,"i-tabler:scale":815,"i-tabler:school":817,"i-tabler:microscope":819,"i-tabler:arrow-up-right":821},{"id":4,"title":5,"author":6,"body":7,"canonical":6,"date":759,"description":760,"extension":761,"image":6,"meta":762,"navigation":767,"ogImage":6,"path":768,"seo":769,"stem":770,"tags":771,"twitterCard":773,"__hash__":774},"blog/blog/7.vision-models-claude-chatgpt-llava.md","Vision Models - Claude vs. GPT 4 Turbo vs. Llava",null,{"type":8,"value":9,"toc":750},"minimark",[10,14,19,22,25,37,40,46,52,60,65,78,83,91,94,98,108,110,115,118,123,128,156,161,228,233,299,302,305,309,312,314,322,324,329,333,433,437,492,496,590,592,595,599,602],[11,12,13],"p",{},"Vision models are a class of models that are designed to understand and interpret visual data. They are used in a wide\nrange of applications, including image classification, object detection, etc. In this blog post, we will compare three\npopular vision models - Claude Haiku from Anthropic, GPT 4 Turbo from OpenAI, and Llava, an open-source model that runs\nlocally. We will compare their performance on image interpretation, profile picture assessment, and identifying complex\nobjects. We will also compare the cost of using these models.",[15,16,18],"h3",{"id":17},"image-interpretation","Image Interpretation",[11,20,21],{},"Just to quickly see how these models interpret an image, we fed them a picture of TinyLlama's logo using Msty's\nsplit chats feature.",[11,23,24],{},"This was the prompt:",[26,27,31],"div",{"className":28},[29,30],"font-medium","italic",[32,33,34],"blockquote",{},[11,35,36],{},"Explain this image",[11,38,39],{},"Here are the results:",[41,42],"blog-image",{"alt":43,"caption":44,"src":45},"Model output comparisons for Claude, GPT 4, and Llava","Claude, ChatGPT, and Llava interpret an image of TinyLlama's logo","/blog/7/explain-image.webp",[11,47,48],{},[49,50,51],"strong",{},"Claude's Haiku interpretation:",[26,53,55],{"className":54},[30],[32,56,57],{},[11,58,59],{},"The image depicts a colorful, stylized illustration of a cute and energetic-looking creature that appears to be a\nfantastical animal, possibly a type of llama or alpaca. The creature has a vibrant, fluffy coat in shades of orange,\nred, and purple, with large expressive eyes and pointed ears. The background is filled with dynamic bursts of color\nand\nabstract shapes, creating a sense of movement and energy around the creature. The overall style of the illustration\nhas\na whimsical, playful, and visually striking quality, capturing the lively and joyful nature of the depicted character.",[11,61,62],{},[49,63,64],{},"Llava's interpretation:",[26,66,68,73],{"className":67},[30],[32,69,70],{},[11,71,72],{},"This is an illustration of a cute, stylized llama or vicuña character that seems to be designed with a friendly and\nwhimsical appearance. The creature has colorful fur in shades of pink, yellow, orange, and white, giving it a playful\nlook. It appears to be running towards the viewer with its front legs raised slightly off the ground as if it's in\nmid-gallop or dashing forward.",[32,74,75],{},[11,76,77],{},"The background is abstract and features vibrant colors that blend together without clear boundaries, which creates a\nsense of motion and energy around the character. The artwork is likely intended for entertainment purposes, possibly\nfor\nchildren given its cartoonish style and appealing nature. It could also be related to video games or animated content\nwhere such characters are commonplace.",[11,79,80],{},[49,81,82],{},"ChatGPT's interpretation:",[26,84,86],{"className":85},[30],[32,87,88],{},[11,89,90],{},"This image features a stylized, animated depiction of an alpaca. The alpaca, drawn in a vibrant and energetic style,\nappears to be leaping or bounding joyfully. It is surrounded by dynamic, colorful bursts and splashes, suggesting\nmotion\nand energy. The color palette is rich, with shades of orange, red, and purple, which adds a playful and magical\nquality\nto the depiction. Overall, the artwork is cheerful and captures a light-hearted, whimsical essence, typical of fantasy\nor cartoon illustrations.",[11,92,93],{},"All 3 models were able to identify the image as a logo and provided some additional context, but, and this is a bit\nsubjective, Llava's interpretation was better than the other in our opinion. It explained not just Llama but also\nexplained the background a bit.",[15,95,97],{"id":96},"profile-picture-assessment","Profile Picture Assessment",[11,99,100,101,107],{},"For the second prompt, we used was a picture from ",[102,103,104],"a",{"href":104,"rel":105},"https://thispersondoesnotexist.com",[106],"nofollow"," and ask the models to assess the\ntraits of the person in the image and make some actionable improvement suggestions.",[11,109,24],{},[32,111,112],{},[11,113,114],{},"Assess the professionalism and approachability of my profile picture; provide actionable improvement suggestions.",[11,116,117],{},"These were the results:",[41,119],{"alt":120,"caption":121,"src":122},"Model assessment of a person's traits","Claude, ChatGPT, and Llava assess the traits of a person in an image","/blog/7/assess-traits.webp",[11,124,125],{},[49,126,127],{},"Claude's Haiku assessment:",[26,129,131,136,141,146,151],{"className":130},[30],[32,132,133],{},[11,134,135],{},"The profile picture appears professional and approachable. The person in the image is smiling warmly, which conveys a\nfriendly and welcoming demeanor. The neutral background and attire suggest a professional setting. A few potential\nimprovements could be:",[32,137,138],{},[11,139,140],{},"1.Ensuring the lighting is even and flattering, as there are some shadows on the face that could be minimized.",[32,142,143],{},[11,144,145],{},"2.Considering a slightly more formal or business-appropriate outfit, such as a collared shirt or blouse, to further\nemphasize the professional tone.",[32,147,148],{},[11,149,150],{},"3.Experimenting with different camera angles or framing to potentially showcase more of the upper body or a wider shot\nof the surroundings.",[32,152,153],{},[11,154,155],{},"Overall, the profile picture effectively communicates a positive, professional, and approachable impression. With a\nfew minor adjustments, it could be even more impactful.",[11,157,158],{},[49,159,160],{},"Llava's assessment:",[26,162,164,169,178,187,196,205,214,223],{"className":163},[30],[32,165,166],{},[11,167,168],{},"The image you've shared is quite pleasant and approachable. Here are some suggestions to enhance your professional\nprofile picture:",[32,170,171],{},[11,172,173,174,177],{},"1.",[49,175,176],{},"Smile",": Your smile is genuine and warm, which helps create a friendly first impression. However, it might be\nhelpful to ensure that both your upper and lower teeth can be seen for more balance in the shot. This creates a sense\nof openness and approachability.",[32,179,180],{},[11,181,182,183,186],{},"2.",[49,184,185],{},"Eye Contact",": While you make eye contact with the camera, maintaining direct gaze while also looking at whoever\nis viewing your profile picture might help create a stronger connection with potential contacts or employers.",[32,188,189],{},[11,190,191,192,195],{},"3.",[49,193,194],{},"Hair and Makeup",": Your hair looks neatly styled and your makeup enhances your natural beauty without overpowering\nit. If you're seeking to convey more professionalism, consider having a hairstyle that is not too casual, depending\non the industry norms of the field you are in.",[32,197,198],{},[11,199,200,201,204],{},"4.",[49,202,203],{},"Attire",": Your attire seems appropriate for a professional setting and does not distract from your face or\nmessage. However, if you're going for a more polished look, ensure clothing is neatly fitted without any visible\nwrinkles that could be perceived as unprofessional.",[32,206,207],{},[11,208,209,210,213],{},"5.",[49,211,212],{},"Background",": The background is simple and doesn't detract attention away from the subject (you). This is ideal\nfor professional use. However, if you want to make a statement about your personality or interests, consider having\nan image with more context that could be relevant to what you do professionally without being too busy or\ndistracting.",[32,215,216],{},[11,217,218,219,222],{},"6.",[49,220,221],{},"Confidence",": You radiate confidence in the picture which is important for professional networking and job\ninterviews. Maintain this confident demeanor during your interactions, both online and offline.",[32,224,225],{},[11,226,227],{},"Remember, these are just suggestions to enhance what seems like a strong profile picture already!",[11,229,230],{},[49,231,232],{},"ChatGPT's assessment:",[26,234,236,241,246,254,262,270,278,286,294],{"className":235},[30],[32,237,238],{},[11,239,240],{},"Your profile picture already exudes a sense of approachability due to your friendly smile and direct eye contact,\nwhich are great traits for making a positive impression. Additionally, your overall appearance is neat and\npresentable,\ncontributing to a professional image.",[32,242,243],{},[11,244,245],{},"Here are a few actionable suggestions for potentially enhancing the professionalism and approachability of your\nprofile picture:",[32,247,248],{},[11,249,173,250,253],{},[49,251,252],{},"Background Considerations",": The current background, although not very distracting, features elements of foliage\nthat might be slightly casual depending on the professional context. Choosing a more neutral background or one that\nis a solid color could convey a more formal and polished image.",[32,255,256],{},[11,257,182,258,261],{},[49,259,260],{},"Lighting",": The lighting in the current photo is good, but ensuring even lighting on the face can further improve\nvisibility and emphasis on facial expressions, providing a smoother and more consistent image.",[32,263,264],{},[11,265,191,266,269],{},[49,267,268],{},"Clothing and Accessories",": While what you are wearing isn't fully visible in the picture, ensuring that your\nattire in the photo aligns with professional attire customary in your field can enhance the professional aspect. For\naccessories, simple and understated options typically work best for professional settings.",[32,271,272],{},[11,273,200,274,277],{},[49,275,276],{},"Hairstyle",": Your current hairstyle looks neat and suits you well; just ensure that hair does not obscure your\nface, as clear visibility of the face is key for approachable and professional images.",[32,279,280],{},[11,281,209,282,285],{},[49,283,284],{},"Facial Expression",": You have a great smiling expression which is very welcoming. For different professional\ncontexts, consider a range of expressions from a warm, approachable smile to a more subdued smile to adjust the level\nof formality.",[32,287,288],{},[11,289,218,290,293],{},[49,291,292],{},"Photography Quality",": Your current picture is of high quality. Always ensure high resolution and sharp focus for\na professional finish. Avoid pixelation or blurring.",[32,295,296],{},[11,297,298],{},"These tips should help adjust or fine-tune your profile picture depending on various professional environments you may\nwish to fit into.",[300,301],"hr",{},[11,303,304],{},"Claude and GPT 4 both provided a detailed assessment of the person's traits and made some actionable improvement but\nthe best assessment and suggestions came from Llava. It was able to provide a more detailed analysis of the person's\ntraits and also suggested some actionable improvements. GPT 4's suggestions were really good as well but Claude's\nsuggestions weren't in depth. This probably is due to the fact that we are using the base model of Claude - the Haiku\nmodel.",[15,306,308],{"id":307},"identifying-and-classifying-complex-objects","Identifying and Classifying Complex Objects",[11,310,311],{},"As a final test, we provide all three models with an image of a complex object - an aquarium with various fish,\nplants, and rocks. We asked them to identify the objects in the image and categorize them.",[11,313,24],{},[26,315,317],{"className":316},[29,30],[32,318,319],{},[11,320,321],{},"Explain this image. For any objects identified, make a table of what they are and their colors and what kingdom they\nbelong to.",[11,323,39],{},[41,325],{"alt":326,"caption":327,"src":328},"Identifying and classifying objects in an image using Claude, GPT 4, and Llava","Claude, ChatGPT, and Llava identify and classify objects in an image of an aquarium","/blog/7/identifying-complex-objects.webp",[11,330,331],{},[49,332,127],{},[26,334,336,341,428],{"className":335},[30],[32,337,338],{},[11,339,340],{},"The image depicts an aquarium or fish tank filled with a variety of aquatic plants and fish. Let's examine the objects\nidentified in the image and create a table with their names, colors, and the kingdom they belong to.",[32,342,343],{},[344,345,346,362],"table",{},[347,348,349],"thead",{},[350,351,352,356,359],"tr",{},[353,354,355],"th",{},"Object",[353,357,358],{},"Color",[353,360,361],{},"Kingdom",[363,364,365,377,387,398,408,419],"tbody",{},[350,366,367,371,374],{},[368,369,370],"td",{},"Angelfish",[368,372,373],{},"Orange, white, and black",[368,375,376],{},"Animalia (Animal)",[350,378,379,382,385],{},[368,380,381],{},"Tetras",[368,383,384],{},"Red and black",[368,386,376],{},[350,388,389,392,395],{},[368,390,391],{},"Aquatic plants",[368,393,394],{},"Green",[368,396,397],{},"Plantae (Plant)",[350,399,400,403,406],{},[368,401,402],{},"Driftwood",[368,404,405],{},"Brown",[368,407,376],{},[350,409,410,413,416],{},[368,411,412],{},"Gravel/substrate",[368,414,415],{},"Black",[368,417,418],{},"Abiotic (Non-living)",[350,420,421,424,426],{},[368,422,423],{},"Aquarium equipment (tubing, etc.)",[368,425,415],{},[368,427,418],{},[32,429,430],{},[11,431,432],{},"The image depicts a well-established and diverse freshwater aquarium ecosystem, with various species of tropical fish,\nsuch as angelfish and tetras, swimming among the lush aquatic plants and driftwood. The plants and gravel/substrate\nprovide a natural-looking environment for the fish to thrive in.",[11,434,435],{},[49,436,160],{},[26,438,440,445,450,455],{"className":439},[30],[32,441,442],{},[11,443,444],{},"This image shows an aquarium containing a diverse collection of tropical fish. The fish in the foreground are\nprimarily yellow and red, suggesting that they may be species from the family Poeciliidae, such as guppies or mollies,\nwhich exhibit bright colors to signal their fitness and attract mates.",[32,446,447],{},[11,448,449],{},"In addition to these brightly colored fish, there are also other less colorful ones in the background. These could\nbelong to different families of tropical fish. The plants within the aquarium provide a naturalistic setting for these\nanimals, helping them blend into their environment while providing shelter and hiding spots.",[32,451,452],{},[11,453,454],{},"Here is a table identifying some objects in the image based on their colors:",[32,456,457],{},[344,458,459,469],{},[347,460,461],{},[350,462,463,465,467],{},[353,464,355],{},[353,466,358],{},[353,468,361],{},[363,470,471,482],{},[350,472,473,476,479],{},[368,474,475],{},"Fish",[368,477,478],{},"Yellow",[368,480,481],{},"Animalia",[350,483,484,487,489],{},[368,485,486],{},"Plants",[368,488,394],{},[368,490,491],{},"Plantae",[11,493,494],{},[49,495,232],{},[26,497,499,504,509,585],{"className":498},[30],[32,500,501],{},[11,502,503],{},"The provided image is of a beautifully maintained aquarium featuring an assortment of fish and aquatic plants. The\naquarium has fish of various sizes and colors, and plants that enhance its ecological aesthetics, alongside some\naquarium equipment like heaters and possibly a filtration system.",[32,505,506],{},[11,507,508],{},"Here is a table describing some visible objects in the image along with their color and biological kingdom:",[32,510,511],{},[344,512,513,524],{},[347,514,515],{},[350,516,517,519,522],{},[353,518,355],{},[353,520,521],{},"Color(s)",[353,523,361],{},[363,525,526,536,546,555,565,574],{},[350,527,528,531,534],{},[368,529,530],{},"Fish (Angelfish)",[368,532,533],{},"Black, white, orange",[368,535,481],{},[350,537,538,541,544],{},[368,539,540],{},"Fish (Tetras)",[368,542,543],{},"Red, black, yellow",[368,545,481],{},[350,547,548,551,553],{},[368,549,550],{},"Aquarium Plants",[368,552,394],{},[368,554,491],{},[350,556,557,560,562],{},[368,558,559],{},"Substrate (Gravel)",[368,561,415],{},[368,563,564],{},"N/A (Mineral)",[350,566,567,569,571],{},[368,568,402],{},[368,570,405],{},[368,572,573],{},"N/A (Material)",[350,575,576,579,582],{},[368,577,578],{},"Heater",[368,580,581],{},"Black, silver",[368,583,584],{},"N/A (Man-made)",[32,586,587],{},[11,588,589],{},"The aquarium scene depicted forms a small ecosystem, providing a habitat that mimics a natural environment for the\nvarious species residing within. The diversity of plants helps in maintaining the oxygen level and the water quality,\nwhich is essential for the health of the fish. The colors of the fish, ranging from stark oranges to subtle greens,\nadd a vivid dynamic to the overall aesthetic appeal of the aquarium.",[300,591],{},[11,593,594],{},"All three models were able to identify the objects in the image and provide a detailed classification. I wasn't\nexpecting them to identify each and every fish and plants in the image. But I was expecting a bit more than what I got.\nHowever, this time GPT 4 Turbo was the best at identifying the objects and providing a detailed classification. It even\nidentified Driftwood, Heater, and Gravel and their colors. Claude wasn't that far behind and given it was the cheapest\nand smallest model, it did a very impressive job. Llava, on the other hand, was the worst at identifying the objects and\nproviding a detailed classification.",[15,596,598],{"id":597},"cost-comparison","Cost Comparison",[11,600,601],{},"Now, let's compare the cost of using these models. Claude is the cheapest model, with a cost of $0.00001351 per\n200x200px image. ChatGPT is the most expensive model, with a cost of $0.00255 per 150x150px image. Llava, on the other\nhand, is a free model since it runs locally. Of course, there is a cost associated with running the model on your local\nmachine, but it is significantly cheaper than using a cloud-based model like Claude or ChatGPT. If you are doing a lot\nof image processing, it might be worth investing in a local model like Llava.",[344,603,604,620],{},[347,605,606],{},[350,607,608,611,614,617],{},[353,609,610],{},"Model",[353,612,613],{},"Image Size",[353,615,616],{},"$ / Image",[353,618,619],{},"$ / 1K Images",[363,621,622,636,649,662,675,687,699,712,724,736],{},[350,623,624,627,630,633],{},[368,625,626],{},"Claude Haiku",[368,628,629],{},"200x200 px",[368,631,632],{},"$0.0000135",[368,634,635],{},"$0.01",[350,637,638,641,643,646],{},[368,639,640],{},"Claude Sonnet",[368,642,629],{},[368,644,645],{},"$0.000162",[368,647,648],{},"$0.16",[350,650,651,654,656,659],{},[368,652,653],{},"Claude Opus",[368,655,629],{},[368,657,658],{},"$0.00081",[368,660,661],{},"$0.81",[350,663,664,666,669,672],{},[368,665,626],{},[368,667,668],{},"1000x1000 px",[368,670,671],{},"$0.000334",[368,673,674],{},"$0.33",[350,676,677,679,681,684],{},[368,678,640],{},[368,680,668],{},[368,682,683],{},"$0.004",[368,685,686],{},"$4.00",[350,688,689,691,693,696],{},[368,690,653],{},[368,692,668],{},[368,694,695],{},"$0.02",[368,697,698],{},"$20.01",[350,700,701,703,706,709],{},[368,702,626],{},[368,704,705],{},"192x1092 px",[368,707,708],{},"$0.000467",[368,710,711],{},"$4.77",[350,713,714,716,719,722],{},[368,715,640],{},[368,717,718],{},"1092x1092 px",[368,720,721],{},"$0.00477",[368,723,711],{},[350,725,726,728,730,733],{},[368,727,653],{},[368,729,718],{},[368,731,732],{},"$0.02385",[368,734,735],{},"$23.85",[350,737,738,741,744,747],{},[368,739,740],{},"GPT4 Vision",[368,742,743],{},"150x150 px",[368,745,746],{},"$0.00255",[368,748,749],{},"$2.55",{"title":751,"searchDepth":752,"depth":752,"links":753},"",2,[754,756,757,758],{"id":17,"depth":755,"text":18},3,{"id":96,"depth":755,"text":97},{"id":307,"depth":755,"text":308},{"id":597,"depth":755,"text":598},"20240417","A comparison of three popular vision models - Claude, ChatGPT, and Llava. We will compare their performance on image interpretation, profile picture assessment, and identifying complex objects. We will also compare the cost of using these models.","md",{"excerpt":763},{"type":8,"value":764},[765],[11,766,13],{},true,"/blog/vision-models-claude-chatgpt-llava",{"title":5,"description":760},"blog/7.vision-models-claude-chatgpt-llava",[772],"Msty 1.x","summary_large_image","NWfhghfGao0lizYRcQLc6LkC-hfbLCovdSSzPVhA_n8",[776,780],{"title":777,"path":778,"stem":779,"children":-1},"Llama 3 vs. GPT-4 vs. Gemini Pro","/blog/llama3-vs-gpt-4-vs-gemini-pro","blog/8.llama3-vs-gpt-4-vs-gemini-pro",{"title":781,"path":782,"stem":783,"children":-1},"Introducing New Prompts Library","/blog/introducing-new-prompts-library","blog/6.introducing-new-prompts-library",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":788},0,24,false,"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"M4 6h16M4 12h16M4 18h16\"/>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":790},"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"m6 9l6 6l6-6\"/>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":792},"\u003Cg fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\">\u003Cpath d=\"M4 13a8 8 0 0 1 7 7a6 6 0 0 0 3-5a9 9 0 0 0 6-8a3 3 0 0 0-3-3a9 9 0 0 0-8 6a6 6 0 0 0-5 3\"/>\u003Cpath d=\"M7 14a6 6 0 0 0-3 6a6 6 0 0 0 6-3m4-8a1 1 0 1 0 2 0a1 1 0 1 0-2 0\"/>\u003C/g>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":794},"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"M5 12h14M5 12l6 6m-6-6l6-6\"/>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":796},"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"M5 12h14m-6 6l6-6m-6-6l6 6\"/>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":798},"\u003Cg fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\">\u003Cpath d=\"M8 12a1 1 0 1 0 2 0a1 1 0 0 0-2 0m6 0a1 1 0 1 0 2 0a1 1 0 0 0-2 0\"/>\u003Cpath d=\"M15.5 17c0 1 1.5 3 2 3c1.5 0 2.833-1.667 3.5-3c.667-1.667.5-5.833-1.5-11.5c-1.457-1.015-3-1.34-4.5-1.5l-.972 1.923a11.9 11.9 0 0 0-4.053 0L9 4c-1.5.16-3.043.485-4.5 1.5c-2 5.667-2.167 9.833-1.5 11.5c.667 1.333 2 3 3.5 3c.5 0 2-2 2-3\"/>\u003Cpath d=\"M7 16.5c3.5 1 6.5 1 10 0\"/>\u003C/g>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":800},"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"m4 4l11.733 16H20L8.267 4zm0 16l6.768-6.768m2.46-2.46L20 4\"/>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":802},"\u003Cg fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\">\u003Cpath d=\"M2 8a4 4 0 0 1 4-4h12a4 4 0 0 1 4 4v8a4 4 0 0 1-4 4H6a4 4 0 0 1-4-4z\"/>\u003Cpath d=\"m10 9l5 3l-5 3z\"/>\u003C/g>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":804},"\u003Cg fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\">\u003Cpath d=\"M8 11v5m0-8v.01M12 16v-5m4 5v-3a2 2 0 1 0-4 0\"/>\u003Cpath d=\"M3 7a4 4 0 0 1 4-4h10a4 4 0 0 1 4 4v10a4 4 0 0 1-4 4H7a4 4 0 0 1-4-4z\"/>\u003C/g>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":806},"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"M7 10v4h3v7h4v-7h3l1-4h-4V8a1 1 0 0 1 1-1h3V3h-3a5 5 0 0 0-5 5v2z\"/>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":808},"\u003Cg fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\">\u003Cpath d=\"M4 8a4 4 0 0 1 4-4h8a4 4 0 0 1 4 4v8a4 4 0 0 1-4 4H8a4 4 0 0 1-4-4z\"/>\u003Cpath d=\"M9 12a3 3 0 1 0 6 0a3 3 0 0 0-6 0m7.5-4.5v.01\"/>\u003C/g>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":810},"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"M21 7.917v4.034A9.95 9.95 0 0 1 16 10v4.5a6.5 6.5 0 1 1-8-6.326V12.5a2.5 2.5 0 1 0 4 2V3h4.083A6.005 6.005 0 0 0 21 7.917\"/>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":812},"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"M8 7a4 4 0 1 0 8 0a4 4 0 0 0-8 0M6 21v-2a4 4 0 0 1 4-4h4a4 4 0 0 1 4 4v2\"/>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":814},"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"M3 21h18M9 8h1m-1 4h1m-1 4h1m4-8h1m-1 4h1m-1 4h1M5 21V5a2 2 0 0 1 2-2h10a2 2 0 0 1 2 2v16\"/>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":816},"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"M7 20h10M6 6l6-1l6 1m-6-3v17m-3-8L6 6l-3 6a3 3 0 0 0 6 0m12 0l-3-6l-3 6a3 3 0 0 0 6 0\"/>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":818},"\u003Cg fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\">\u003Cpath d=\"M22 9L12 5L2 9l10 4zv6\"/>\u003Cpath d=\"M6 10.6V16a6 3 0 0 0 12 0v-5.4\"/>\u003C/g>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":820},"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"M5 21h14M6 18h2m-1 0v3m2-10l3 3l6-6l-3-3zm1.5 1.5L9 14m8-11l3 3m-8 15a6 6 0 0 0 3.715-10.712\"/>",{"left":785,"top":785,"width":786,"height":786,"rotate":785,"vFlip":787,"hFlip":787,"body":822},"\u003Cpath fill=\"none\" stroke=\"currentColor\" stroke-linecap=\"round\" stroke-linejoin=\"round\" stroke-width=\"2\" d=\"M17 7L7 17M8 7h9v9\"/>",1776358792956]