A sample prompt of what you can find in this page
Prompt by bads

Its branches Nano Banana prompts

very few results

1 month ago

A dreamlike autumn forest unfolds in layers of delicately cut paper. The foreground shows crisp, oversized autumn leaves in shades of burnt orange, golden yellow, and deep crimson, their edges curling like lace. Some leaves float mid-air, suspended as if gravity has paused, their shadows layered on pale textured paper ground. The middle layer reveals a winding path made of folded parchment, leading toward a glowing paper-cut tree whose branches split into impossible shapes—spirals, fractals, and delicate origami folds. Each branch holds a different scene: one has a tiny paper boat sailing along its veins, another a house perched upside-down like a dream. Lanterns shaped like acorns dangle, glowing with soft amber light. In the background, the sky is a collage of layered translucent vellum in warm amber, deep violet, and smoky gray. Through it, a giant crescent moon cut from silver foil hovers, its surface patterned with filigree swirls. Paper-cut stars dangle from invisible strings like a handmade mobile. Surreal elements punctuate the scene: A flock of origami deer made of folded autumn leaves leap across the horizon. Mushrooms, cut from crimson and cream paper, glow with a surreal bioluminescence. A river of golden paper ribbons winds through the scene, reflecting autumn light. The entire composition feels handcrafted—layer upon layer of cut, folded, and textured papers stacked to create depth, shadows, and dreamlike atmosphere. The lighting emphasizes the tactile paper edges, making it both whimsical and surreal.

28 days ago

Scientific infographic illustrating an AI-driven closed-loop framework for virtual molecular library construction, showing the adaptive cycle of “Representation – Generation – Prediction – Feedback”. Central theme: artificial intelligence empowering drug discovery and molecular design. The diagram is a circular workflow structure centered on the AI virtual molecular library system. Left module: Representation Learning, visualized with neural network icons, molecular graphs, protein structures, and amino acid sequence symbols, representing molecular and protein feature embeddings. Upper-right module: Molecular Generation, showing diffusion or VAE-like model generating diverse small molecules, arrows indicating exploration of chemical space, novelty, and synthesizability constraints. Lower-right module: Property Prediction, containing ADMET, activity, and selectivity metrics represented by radar charts or data panels, feeding results back to the representation module to close the loop. Bottom section: Evolution from virtual to drug-like molecular libraries, shown as a smooth gradient arrow with multi-objective optimization icons balancing drug-likeness and diversity. Right-side branch: Pretrained models for new target ligand design, divided into three submodules—small molecule pretraining, protein pretraining, and cross-modal pretraining (protein–ligand interaction)—depicting embedding fusion or contrastive learning in shared latent space. No human figures, only abstract scientific symbols and molecular visuals. Style: flat vector scientific infographic, modern and minimalistic, clear logical flow, smooth connections between modules. Color scheme: blue for AI and representation, orange-yellow for generation, green for prediction; background light gray or white. Typography: clean sans-serif labels, concise annotations. High resolution (≥600 dpi), suitable for journal publication, ultra-clear, balanced layout, professional academic tone.