A prompt comparing GPT-image-2.5, Nano Banana 2
Social media post desert solitary smoke landscape comparison
A prompt comparing GPT-image-2.5, Nano Banana 2 (nano-banana-pro), and Grok-imagine2 on generating a desolate desert landscape with solitary smoke.
Overview
A prompt comparing GPT-image-2.5, Nano Banana 2 (nano-banana-pro), and Grok-imagine2 on generating a desolate desert landscape with solitary smoke.
The prompt
| 1 | Desert solitary smoke northwest scenery blockbuster, dusk at the edge of Mingsha Mountain in Dunhuang, Gansu, clear and dry northwest autumn evening. Foreground features wind-eroded dune ridges and a dead populus euphratica tree, branches twisted pointing to the sky, sand surface has clear wind patterns; Midground shows a straight column of solitary smoke rising gracefully from behind the dunes, stretching into a thin pillar against the backlight; Background features continuous golden sea of sand layered with Qilian Mountain snow line, a low-hanging setting sun on the horizon, clouds dyed in pale purple and honey gold. Air floats with fine sand particles and warm-colored dust mist, backlight outlines the contrast between light and shadow on the dunes. Lighting: Low-angle warm golden side-backlight, color temperature approx 3200K, sunny side of dunes is honey gold, shady side is cold gray-blue, forming warm-cold contrast. Camera: 24mm wide angle, low position close to sand surface, f/8 deep depth of field, rule of thirds composition, horizon pressed to lower third of frame, sky whitespace occupies two-thirds. Color grading: Eastmancolor film simulation, warm gold vs gray blue contrast, slight film grain, slight vignette. Ultra detailed, photorealistic landscape photography, National Geographic style. No people, No oil painting, No anime, No 3D render, No text, No watermark. |
Connects with Agent Alley MCP · agentalley.io/mcp
Details
- License
- CC-BY-4.0
- Source
- youmind.com ↗
- Creator
- Candy · 3 listings
Similar prompts
See all →
SkillMake Japanese TV-anime style videos with codeAnime cel
edenfunf/reelmimic · by edenfunfMake Japanese TV-anime style videos (MP4) with code — cel-shaded characters with tapered line art, big detailed eyes, hair clumps with a specular band, comedic anime reactions (sweat drop, anger vein, sparkle eyes, ≥< eyes, dot eyes, tears), painted skies with cumulus clouds, school/street/classroom/rooftop sets with time-of-day palettes, speed/focus lines, impact frames, dramatic zooms, smears, sakura petals and anime subtitles (CJK). Canvas 2D rendered frame by frame in headless Chrome, encoded with ffmpeg. Use when a reference video or brief calls for anime / 動畫 / 日系動畫 / アニメ / cel-shaded / slice-of-life / school romance / shōnen-style reactions, or when the video-clone router picks the anime-cel style. 2D only; characters are original (Hina, Ren) or new ones built on the same rig.★ 3.6k GitHub stars
SkillDirect and produce a short film made entirely in codeLemo opuscar
lemomo-ai/lemo-opuscar · by lemomo-aiDirect and produce a short film made entirely in code, in one of the styles of the Lemo-Opuscar library (e.g. Impasto Oil Painting 油画厚涂, Watercolor Brush 水彩笔刷, Ukiyo-e 浮世绘, Satellite Briefing 卫星简报, Exploded Teardown 产品拆解, Microscope Story 显微叙事). Use when the user asks for a video, film, short, promo, explainer or animation (视频、短片、动画、宣传片) in a named style, including data, science and product explainers built from real material such as satellite imagery, laser scans, CAD files or archive scans (数据解说、科普、产品拆解); when they want a film made about their own topic and haven't chosen a style (help them choose); or when they ask which film styles there are. Not for editing or converting existing video files.★ 3k GitHub stars
SkillGenerate Ian-style Xiaohei illustrations for articles, posts
dzhng/skills · by dzhngGenerate Ian-style Xiaohei illustrations for articles, posts, blogs, Notion documents, workflows, methods, processes, structures, states, metaphors, and opinions. Use when the user asks for weird, hand-drawn, Xiaohei, article, editorial, body illustrations, illustration ideas, shot lists, title removal, image edits, or image regeneration. By default, all image text and annotations are English, even when the source article is Chinese; only use another language when the user explicitly asks.★ 1.3k GitHub stars
SkillCreating game art through Scenario MCP: spritesScenario game assets
scenario-labs/skills · by scenario-labsUse when creating game art through Scenario MCP: sprites, sprite sheets, icons, props, loot, tilesets and autotile terrain transitions, seamless tiles, isometric buildings, top-down maps, pixel art, UI buttons and panels, parallax background layers or depth planes for side-scrollers, and character or concept art; or when assets need transparent backgrounds, background removal, style-consistent variation batches, upscaling, pixel-grid cleanup, or PNG export for Unity, Godot, or Unreal.★ 854 GitHub stars
SkillTrain custom LoRAs with ostris AI-ToolkitAI-Toolkit LoRA Trainer (WAN 2.2 & Z-Image)
artokun/comfyui-mcp · by artokunTrain custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prep, key params, and using the result in a ComfyUI workflow.★ 759 GitHub stars
SkillAnime/illustration text-to-imageANIMA 1.0 (Anima Base Ultra) Text-to-Image Workflowsartokun/comfyui-mcp · by artokunAnime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT). Use for anime, manga, illustrated characters; accepts Danbooru tags + natural language; runs/trains on <6GB VRAM; includes anime inpainting via Anima-LLLite ControlNet★ 759 GitHub starsMore from Candy
PromptA prompt comparing GPT-image-2.5, Nano Banana 2 Product marketing transparent material still life comparison
YouMind-OpenLab/awesome-nano-banana-pro-prompts · by CandyA prompt comparing GPT-image-2.5, Nano Banana 2 (nano-banana-pro), and Grok-imagine2 on rendering transparent materials like glass, water, and light.New listing
PromptA detailed prompt for generating a photorealistic portraitProfile / Avatar - Retro Hong Kong Cha Chaan Teng Portrait PromptYouMind-OpenLab/awesome-nano-banana-pro-prompts · by CandyA detailed prompt for generating a photorealistic portrait of a woman in a retro Hong Kong cafe setting, used in a comparison between GPT-image-2.5, Nano Banana 2, and Grok-imagine2.New listing