[{"data":1,"prerenderedAt":179},["ShallowReactive",2],{"project-43924702":3},{"id":4,"name":5,"line":5,"line_source":6,"title":7,"url":8,"domain":9,"maker":10,"posted_at":11,"year":12,"points":13,"comments":14,"rank_in_year":15,"shown_in_year":16,"top":17,"tier":18,"category":19,"subcategory":20,"format":21,"keywords":22,"reception":27,"sentiment":28,"stance_mix":29,"scored_comments":33,"aspects":34,"strip":38,"post_text":40,"what":41,"said":63,"maker_in_thread":110,"shape":119,"grid":121,"attempts":140,"same_week":141,"maker_shows":31,"maker_hidden":171,"reader_version":172,"card":173},"43924702","An AI-first visual editor using GPT-4o's GPT-image-1 model","title","Show HN: An AI-first visual editor using GPT-4o's GPT-image-1 model","https:\u002F\u002Fimg.ly\u002Fblog\u002Fai-first-visual-editor-for-gpt-4o-image-gen\u002F","img.ly","buss_jan",1746698379,2025,23,8,1886,3837,50,"shown","creative","ai image editor","web_app",[20,23,24,25,26],"gpt-image-1","visual editor","image generation","canvas editor","curious",0.125,{"positive":30,"neutral":31,"mixed":32,"critical":32},1,4,0,5,{"execution":35,"performance":36,"idea":37},{"positive":32,"critical":32},{"positive":30,"critical":32},{"positive":32,"critical":32},[39,39,32,32,39,39,32,33],3,"Hey HN! We’ve been experimenting with integrating multimodal models directly into creative workflows, and ended up building an AI-first image editor using OpenAI’s new `gpt-image-1` (from GPT-4o) inside our SDK.\n\nInstead of prompting in ChatGPT and pasting outputs into a design tool, this lets you generate, edit, and remix images all in one canvas. This allows for really interesting new workflows, like quickly mixing multiple images, or creating visual prompts by using annotations and reference on the canvas.\n\nSome key details:\n\n- Built with our plugin system in CE.SDK (CreativeEditor SDK) - W",{"problem":42,"audience":48,"pricing":48,"motivation":49,"time_to_build":48,"stack":53,"openness":62,"stage":62,"team_size":62},{"value":43,"source":44,"evidence":45},"Switching between ChatGPT and a design tool to generate and edit images","maker",[46],{"id":47},"post",null,{"value":50,"source":44,"evidence":51},"Experimenting with integrating multimodal models into creative workflows",[52],{"id":47},[54,58],{"value":55,"source":44,"evidence":56},"CE.SDK (CreativeEditor SDK) plugin system",[57],{"id":47},{"value":59,"source":44,"evidence":60},"OpenAI gpt-image-1 model",[61],{"id":47},"unknown",{"praise":64,"objections":77,"requests":85,"questions":93,"alternatives":105},[65],{"value":66,"source":67,"evidence":68},"Impressive and very cool demo","commenter",[69,73],{"id":70,"by":71,"text":72},"43924827","OriginalMrPink","impressive...can't wait for OpenAI to make their image gen faster tough",{"id":74,"by":75,"text":76},"43924725","klaudial","Cool! How does this compare to what tools like Canva or Adobe offer for automation?",[78],{"value":79,"source":67,"evidence":80},"Image generation is slow",[81],{"id":82,"by":83,"text":84},"43924773","GoezdeB","Really interesting! I noticed it takes quite a long to generate images, what’s your take on managing latency?",[86],{"value":87,"source":67,"evidence":88},"Open source parts of the project",[89],{"id":90,"by":91,"text":92},"43924796","_robin_","Looks very cool, any plans to open source parts of this or is it all part of your SDK?",[94,101],{"value":95,"source":67,"evidence":96},"How real-time sync between GPT-4o and the editor works",[97],{"id":98,"by":99,"text":100},"43924840","olcioszek","I'm curious about the architecture behind this integration — how does the system handle communication between GPT-4o and the visual editor in real time? Are there any challenges…",{"value":102,"source":67,"evidence":103},"How latency is managed",[104],{"id":82,"by":83,"text":84},[106],{"value":107,"source":67,"evidence":108},"Canva and Adobe automation",[109],{"id":74,"by":75,"text":76},{"comments":111,"answered":111,"key":112},2,[113,116],{"id":114,"text":115},"43924874","Hey, yes, that's somewhat unavoidable given that is simply takes OpenAI that long to generate images. I think that's to be expected by most users. We tried to be as friendly as…",{"id":117,"text":118},"43924880","Well, it's fundamentally inspired by what these companies are trying to do. However, we are an SDK so we want to offer a toolset for other apps to build similar experiences.",{"commenters":120,"max_depth":111,"maker_replies":111,"first_comment_mins":33,"lifespan_hours":30},7,[122,124,126,130,132,134,136,138],[98,32,39,123,99,32],"project\u002Fneutral\u002Fexecution",[82,30,39,125,83,32],"project\u002Fneutral\u002Fperformance",[127,30,32,128,129,32],"43924839","other\u002Fneutral\u002Fperformance","nablahero",[114,30,32,131,10,30],"maker\u002Fneutral\u002Fperformance",[90,111,39,133,91,32],"project\u002Fneutral\u002Fnone",[74,39,39,135,75,32],"project\u002Fneutral\u002Fidea",[117,39,32,137,10,30],"maker\u002Fneutral\u002Fidea",[70,31,33,139,71,32],"project\u002Fpositive\u002Fperformance",[],[142,147,152,157,162,167],{"id":143,"name":144,"points":145,"category":146},"43935394","Hyvector",331,"dev_tools",{"id":148,"name":149,"points":150,"category":151},"43928118","qtap",259,"infrastructure",{"id":153,"name":154,"points":155,"category":156},"43975423","HelixDB",237,"data",{"id":158,"name":159,"points":160,"category":161},"43988381","Muscle-Mem",226,"ai",{"id":163,"name":164,"points":165,"category":166},"43936097","Aberdeen",224,"languages",{"id":168,"name":169,"points":170,"category":161},"43964201","Airweave",176,false,"v2",{"id":174,"name":5,"line":5,"ai":171,"cat":19,"year":12,"points":13,"comments":14,"rec":27,"s":175,"top":17,"kw":176,"maker":10,"domain":9,"tier":18,"attempts":32,"strip":177,"url":8,"mix":178,"praise":66,"objection":79,"sub":20},43924702,0.13,[20,23,24,25,26],"33003305",[30,31,32,32],1794036674464]