GPT Image Hub
프롬프트 라이브러리
생성
비디오
캔버스
모델
도구
내 컬렉션
가격
한국어
로그인
가입
신규: GPT Image 2.5 Flare와 Sunburst. 가입하면 3장 무료, 이후 장당 8 크레딧.
GPT Image 2.5 사용해 보기
이미지 스튜디오
모델
GPT IMAGE 2
프롬프트
2,611 / 1,000
Dark futuristic dashboard infographic screenshot for [LLMFIT RECOMMENDATIONS], displaying local AI model performance metrics on an ultrawide desktop panel. Setting & Canvas: Ultra-wide 21:9 ratio computer monitor UI screenshot. Dark theme with pitch black and deep teal background, subtle ambient backlight glow, thin glowing neon cyan borders, fine scanline grid texture, and compact sci-fi terminal styling. Header: Top bar displays small label "LEGION / MODEL INTELLIGENCE", primary large title "[LLMFIT RECOMMENDATIONS]", subtitle "NVIDIA GeForce RTX 5090 · 31.84 GB VRAM · 125.18 GB RAM", and a square close-box icon on the top right. Left Panel (two-thirds width): Main card titled "LEGION MODEL LOADOUT" ("LEGION" in neon lime, remainder in white techno font). Exactly 4 horizontal hardware status tiles beneath: 1) NVIDIA GeForce RTX 5090, 31.8 GB VRAM with GPU icon; 2) Intel(R) Core(TM) Ultra 9 285K with CPU chip icon; 3) 125.2 GB system RAM with RAM module icon; 4) CUDA with circular CUDA emblem. Below hardware tiles, exactly 6 ranked rows with lime numbered badges (01-06), displaying model path, quantization, engine runtime, memory footprint, and token speed: 1) shawnw3j/Huihui-Qwen3.6-27B-abliterated-AWQ-MTP — AWQ-4bit — vLLM — 14.7 GB — 80.9 estimated tok/s 2) Vortex5/G4-Starry-Ocean-12B — Q8_0 — llama.cpp — 16 GB — 82.8 estimated tok/s 3) shawnw3j/Qwen3.6-27B-AWQ-MTP — AWQ-4bit — vLLM — 14.7 GB — 80.9 estimated tok/s 4) Minachist/Qwen3.6-27B-INT8-Autoround-V2 — AutoRound-4bit — vLLM — 16.6 GB — 80.9 estimated tok/s 5) exnivo/Qwen3.8-20B-Minitron — Q8_0 — llama.cpp — 22.6 GB — 49.9 estimated tok/s 6) Lorbus/Qwen3.6-27B-int4-AutoRound — AutoRound-4bit — vLLM — 16.6 GB — 80.9 estimated tok/s Bottom of left card features a centered neon divider with text: "ESTIMATED BY LLMFIT · VERIFY WITH A LOCAL BENCHMARK." Right Panel (one-third width): Titled "VERIFIED LLMFIT DATA" with subtitle "ESTIMATES, NOT BENCHMARKS". Lists exactly 6 compact verification cards numbered 01 to 06 in lime font, gray subtext, and cyan performance metrics: 80.9, 82.8, 80.9, 80.9, 49.9, 80.9 tok/s. Bottom warning note in orange: "llmfit recommendations are estimates from detected hardware, not measured benchmarks." Footer: Bottom left displays timestamp "GENERATED 8/17/2026, 7:53:32 PM". Bottom right features a lime-outlined clickable button labeled "[Refresh scan]" with a sync icon. Style & Constraints: Crisp, sharp digital HUD UI graphic, high-contrast condensed sans-serif technical typography, angular framing, no real-life humans or external photography, pure technical dashboard graphic.
Ctrl / ⌘ + Enter
참조 이미지
0 / 16
여기에 참조 이미지를 드롭하세요.
PNG, JPG, WebP · 50 MB
종횡비
자동
품질
보통
해상도
1K
이미지 수
1 / 4
결과
프롬프트로 시작
생성된 이미지가 여기에 표시됩니다.
영감을 얻으세요
제품 사진
인테리어 디자인
소셜 미디어 광고