synabun 2.0.9 → 2.1.0

package/skills/leonardo/modules/image-prompter.md

@@ -1,283 +0,0 @@
-# Image Prompter — Guided Questionnaire
-
-Guide the user through creating the perfect image on Leonardo.ai. Ask questions using an interactive choice prompt, then engineer the optimal prompt and configure all browser settings.
-
-**Important:** This is a browser-based workflow. After the questionnaire, you'll set all parameters in the Leonardo.ai UI using browser tools, then fill the prompt and click Generate.
-
-**Runtime compatibility:** An **interactive choice prompt** means an interactive option card the user clicks — not plain text choices.
-- **Claude Code (REQUIRED path):** `AskUserQuestion` is a deferred tool — its schema is not loaded by default. Before the first prompt in this skill, call `ToolSearch` with query `select:AskUserQuestion` to load it, then call `AskUserQuestion` with 2-4 options. NEVER write the choices as plain text — the sidepanel will render text as static markdown, not an interactive card.
-- **OpenCode (REQUIRED path):** call the native `question` tool — the sidepanel renders it as an interactive card via the `/question.asked` event. NEVER write the choices as plain text.
-- **Codex (REQUIRED path):** call `request_user_input` — the sidepanel renders it as an interactive card. NEVER write the choices as plain text.
-- **Other runtimes:** only when no interactive tool exists, fall back to a concise plain-text multiple-choice question and wait for the user's reply.
-
----
-
-## Phase 1 — Vision (What do you want to create?)
-
-Ask the user to describe their image concept. If `$TOPIC` was set by the router, use it as the starting point and skip asking — but still categorize it.
-
-**Do NOT use an interactive choice prompt here** — this requires free-text input. Output a natural chat message:
-
-> **What kind of image do you want to create?**
-> Describe your vision — subject, scene, mood, purpose. You can also paste or drag reference images for inspiration.
-
-Wait for the user's typed response. After they respond, categorize into one of:
-- **Portrait/People** — headshots, characters, fashion, editorial
-- **Landscape/Architecture** — environments, buildings, scenery
-- **Product/Commercial** — product shots, e-commerce, branding
-- **Illustration/Art** — concept art, digital painting, fantasy
-- **Abstract** — patterns, textures, experimental
-- **Photography** — street, documentary, lifestyle
-- **Logo/Design** — logos, icons, typography, posters
-- **Anime/Manga** — anime-style characters, manga illustrations
-- **Sci-Fi/Fantasy** — futuristic, otherworldly, imaginative
-
-Store as `$CATEGORY`.
-
----
-
-## Phase 2 — Model Selection
-
-Present model options based on `$CATEGORY`. Use an interactive choice prompt:
-
-> **Which image model should we use?**
-
-- **Auto (Recommended)** — "I'll pick the best model for your concept"
-- **Lucid Origin** — "Free, unlimited. Excellent prompt adherence and text rendering, HD output"
-- **Lucid Realism** — "Free, unlimited. Best for cinematic shots, pairs great with video generation"
-- **FLUX Dev** — "Free, unlimited. Detailed, realistic images with style/content reference support"
-- **FLUX Schnell** — "Free, unlimited. Fast, quality outputs"
-- **Phoenix 1.0** — "Free, unlimited. Great prompt adherence, text rendering, image-to-image support"
-- **Seedream 4.5** — "Premium. Best for posters, logos, and text-heavy designs"
-- **FLUX.2 Pro** — "Premium. Advanced prompt adherence with high-fidelity results"
-- **GPT Image-1.5** — "Premium. Superior editing control and detail preservation"
-- **Ideogram 3.0** — "Premium. Best text rendering and consistent generation"
-- **Let me choose from all models** — "Show me the full list"
-
-If **Auto**, select based on category:
-| Category | Recommended Model | Why |
-|----------|------------------|-----|
-| Portrait/People | Lucid Realism | Cinematic realism, free |
-| Landscape/Architecture | FLUX.2 Pro or FLUX Dev | High fidelity |
-| Product/Commercial | GPT Image-1.5 | Editing control |
-| Illustration/Art | FLUX Dev or Phoenix 1.0 | Creative flexibility |
-| Abstract | FLUX Dev | Style/content ref support |
-| Photography | Lucid Realism | Photorealistic |
-| Logo/Design | Seedream 4.5 or Ideogram 3.0 | Text rendering |
-| Anime/Manga | Phoenix 1.0 | Preset support |
-| Sci-Fi/Fantasy | FLUX.2 Pro | High fidelity |
-
-Store as `$MODEL`.
-
----
-
-## Phase 2.5 — Reference Images (Optional)
-
-Check if the user attached images with their **current message** (file paths appear at the top of the prompt). Do NOT check `image_staged` here — old staged images are not reference candidates.
-
-**If images are attached to the current message**, present options based on the selected model's capabilities. Use an interactive choice prompt:
-
-> **You have N reference image(s) available. How should Leonardo use them?**
-
-Options — show ONLY those supported by `$MODEL` (see model-advisor.md capability table):
-
-| Reference Type | Supported By | What It Does |
-|----------------|-------------|--------------|
-| **Image Reference** | Nano Banana 2, Seedream 4.5, GPT Image-1.5, Nano Banana Pro, FLUX.1 Kontext | Use image as direct visual reference |
-| **Style Reference** | Lucid Origin, Lucid Realism, FLUX Dev, FLUX Schnell, Phoenix 1.0/0.9 | Extract and apply the visual style |
-| **Content Reference** | Lucid Origin, Lucid Realism, FLUX Dev, FLUX Schnell, Phoenix 1.0/0.9 | Extract and match the content/composition |
-| **Character Reference** | Phoenix 1.0, Phoenix 0.9 | Maintain character consistency |
-| **Image-to-Image** | Phoenix 1.0, Phoenix 0.9 | Transform the reference into a new image |
-| **Skip** | — | "Don't use reference images" |
-
-If the selected model supports NONE of the reference types, inform the user and skip: *"[Model] doesn't support reference images. Continuing without."*
-
-Store as `$REFERENCE_TYPE` and `$REFERENCE_PATHS`.
-
-**If no images are attached**, ask the user if they'd like to use reference images. First check if `$MODEL` supports any reference types from the table above — if it supports NONE, skip this phase silently.
-
-If the model supports at least one reference type, use an interactive choice prompt:
-
-> **Would you like to use reference images?**
-> Reference images let Leonardo match a style, composition, or visual from an existing image.
-
-- **Yes** — "I have images I'd like to use as reference"
-- **No** — "Continue without reference images"
-
-If **Yes**, respond with this message (plain text, not an interactive choice prompt):
-
-> **Attach your reference image(s) to the chat.**
-> Copy the message below, paste it in the input box, attach your images, and send:
-> ```
-> Here are my reference images
-> ```
-
-Then wait for the user's next message. Check for file paths at the top of their message and also check `image_staged` (action: "list", type: "attachment") for newly attached images. If images are found, proceed with the reference type selection above (the "If images are attached" flow). If no images were found, inform the user no images were detected and ask them to try again or skip.
-
-If **No**, continue to Phase 3.
-
----
-
-## Phase 3 — Style Preset
-
-Use an interactive choice prompt:
-
-> **What visual style do you want?**
-
-- **Dynamic** (default) — "Balanced, versatile style for most subjects"
-- **Cinematic** — "Film-like quality with dramatic lighting and depth"
-- **Creative** — "Artistic, painterly, experimental"
-- **Vibrant** — "Bold colors, high saturation, punchy"
-- **Portrait** — "Optimized for faces and people"
-- **Fashion** — "Editorial, high-fashion aesthetic"
-- **Stock Photo** — "Clean, commercial, stock photography look"
-- **None** — "No style preset — full prompt control"
-
-**Auto-recommendation by category:**
-| Category | Recommended Style |
-|----------|------------------|
-| Portrait/People | Portrait or Cinematic |
-| Landscape/Architecture | Dynamic or Cinematic |
-| Product/Commercial | Stock Photo or Dynamic |
-| Illustration/Art | Creative |
-| Abstract | Creative or None |
-| Photography | Dynamic or Cinematic |
-| Logo/Design | None or Dynamic |
-| Anime/Manga | Dynamic or Creative |
-| Sci-Fi/Fantasy | Cinematic or Creative |
-
-Present the recommendation but let them choose.
-
-Store as `$STYLE`.
-
----
-
-## Phase 4 — Dimensions & Composition
-
-Use an interactive choice prompt:
-
-> **What dimensions/aspect ratio?**
-
-- **Square (1:1)** — "1024x1024. Versatile, social media, profile pictures"
-- **Portrait (2:3)** — "Tall format. People, Pinterest, posters"
-- **Landscape (16:9)** — "Wide format. Wallpapers, headers, cinematic"
-- **Custom** — "Choose from social presets or set a custom ratio"
-
-If **Custom**, offer social/device presets:
-- **Twitter/X (4:3)** — "Timeline-optimized"
-- **Instagram (4:5)** — "Feed-optimized, tall"
-- **TikTok (9:16)** — "Vertical, full-screen"
-- **Desktop (16:9)** — "Widescreen wallpaper"
-
-Store as `$DIMENSIONS`.
-
----
-
-## Phase 5 — Quantity & Details
-
-Use an interactive choice prompt:
-
-> **How many images do you want?**
-
-- **1** — "Single image, fastest"
-- **2** — "Two variations to compare"
-- **3** — "Three options"
-- **4** — "Four variations, maximum choice"
-
-Store as `$NUM_IMAGES`.
-
----
-
-## Phase 5.5 — Creative Brief
-
-You've gathered all the technical settings. Now get the user's **detailed creative vision** before engineering the prompt.
-
-**Do NOT use an interactive choice prompt here** — this requires free-text input. Output a natural chat message summarizing the config and asking for the detailed description:
-
-> **Here's your setup:**
-> - **Model:** $MODEL
-> - **Style:** $STYLE
-> - **Dimensions:** $DIMENSIONS
-> - **Images:** $NUM_IMAGES
-> [If reference images: **Reference:** $REFERENCE_TYPE with N image(s)]
->
-> **Now describe your image in detail.**
-> What's the subject? The scene, composition, lighting, mood, colors? Any specific elements you want included or avoided? The more detail you give, the better I can craft the prompt.
-
-Wait for the user's typed response. Store their detailed description as `$CREATIVE_BRIEF`. This replaces the brief Phase 1 concept as the **primary input** for prompt engineering below.
-
----
-
-## Phase 6 — Prompt Engineering
-
-Now engineer the optimal prompt using `$CREATIVE_BRIEF` (the user's detailed description from Phase 5.5) combined with the style context from earlier phases. Follow these rules:
-
-### Image Prompt Rules
-1. **Subject first** — the main focus of the image
-2. **Materials & texture** — "brushed aluminum", "weathered oak", "silk fabric"
-3. **Lighting is critical** — "rim lighting", "soft diffused north-facing window", "dramatic chiaroscuro"
-4. **Camera language for photorealistic** — "85mm f/1.4", "wide-angle 24mm", "macro close-up"
-5. **Art medium for illustrations** — "oil painting", "watercolor wash", "digital concept art"
-6. **Color palette** — "muted earth tones", "neon pink and teal", "monochromatic blue"
-7. **Avoid vague words** — never "beautiful", "stunning", "amazing", "nice"
-8. **1-3 sentences** — concise, every word counts
-9. **Negative prompt for realism** — remove unwanted elements
-
-### Prompt Structure Template
-```
-[Subject and action], [environment/setting], [lighting description], [camera/art style], [color and mood]
-```
-
-### Example Transformations
-**User says:** "A portrait of a woman"
-**Engineered:** "Editorial portrait of a woman in her 30s with natural curly hair, wearing a charcoal linen blazer against a blurred urban backdrop, shot at 85mm f/1.4 with soft window light from the left creating gentle catchlights, muted warm tones with shallow depth of field"
-
-**User says:** "A fantasy castle"
-**Engineered:** "Towering Gothic castle carved into a sea cliff face, waves crashing against dark volcanic rock below, twilight sky with scattered cirrus clouds catching the last amber light, ravens circling the highest tower, painted in the style of detailed fantasy concept art, deep blues and warm amber highlights"
-
-**User says:** "A product shot of sneakers"
-**Engineered:** "Pair of white minimalist sneakers floating on a clean gradient background, studio lighting with soft shadows, 3/4 angle view showing sole detail, crisp commercial photography with even diffused lighting, neutral tones with bright white product pop"
-
-### Build the prompt
-Using `$CREATIVE_BRIEF` from Phase 5.5 and all style context, craft the perfect prompt.
-
-**You MUST display the engineered prompt before asking for review.** Show it in a formatted block:
-
-> **Engineered Prompt:**
-> ```
-> [your engineered prompt here]
-> ```
-> [If negative prompt: **Negative:** `[negative prompt]`]
-
-Then use an interactive choice prompt for review:
-> **How does this prompt look?**
-- **Looks good — generate** — "Use this prompt as-is and proceed to generation"
-- **Tweak it** — "I want to adjust the prompt before generating"
-- **Rewrite it** — "Start the prompt from scratch with different direction"
-
-If **Tweak it**: ask what they want changed (plain text, not an interactive choice prompt), apply changes, show the updated prompt, and ask again.
-If **Rewrite it**: ask for new direction (plain text), re-engineer from scratch, show the new prompt, and ask again.
-
-### Build negative prompt (if applicable)
-For photorealistic images: "blurry, low quality, deformed, distorted, extra limbs, text, watermark, signature, cropped"
-For illustration/art: "photographic, hyperrealistic, 3D render" (if you want to stay painterly)
-For product shots: "busy background, shadows, reflections, text, hands, people"
-
----
-
-## Output
-
-Once all phases complete, output the final configuration:
-
-```
-$IMAGE_PARAMS:
-  type: image
-  model: $MODEL
-  style: $STYLE
-  dimensions: $DIMENSIONS
-  num_images: $NUM_IMAGES
-  prompt: "[engineered prompt]"
-  negative_prompt: "[if any]"
-```
-
-Return to SKILL.md Step 3 for browser execution.

package/skills/leonardo/modules/model-advisor.md

@@ -1,100 +0,0 @@
-# Model Advisor — Reference Guide
-
-Quick reference for Leonardo.ai model selection. Use this when you need to recommend the best model for a specific use case.
-
----
-
-## Image Models — Decision Matrix
-
-| Use Case | Best Model | Why | Cost |
-|----------|-----------|-----|------|
-| Photorealistic portraits | Lucid Realism | Cinematic realism, pairs w/ video | Unlimited |
-| Product photography | GPT Image-1.5 | Superior editing & detail | Paid |
-| Landscapes & architecture | FLUX.2 Pro | High-fidelity, prompt adherence | Paid |
-| Concept art & illustration | FLUX Dev | Creative flexibility, style ref | Unlimited |
-| Anime/Manga | Phoenix 1.0 + style preset | Preset support, character ref | Unlimited |
-| Text in images / logos | Ideogram 3.0 or Seedream 4.5 | Best text rendering | Paid |
-| Quick iterations | FLUX Schnell | Fastest free model | Unlimited |
-| Maximum quality | Seedream 4.5 | Ultra quality, posters/logos | Paid |
-| Style transfer / editing | FLUX.1 Kontext Max | Precise control, max quality | Paid |
-| Context-aware editing | Nano Banana 2 | Fast, sharp, simple editing | Paid |
-| HD with text rendering | Lucid Origin | Prompt adherence + text + HD | Unlimited |
-| Consistency & infographics | Nano Banana Pro | Gemini 3 Pro based | Paid |
-| Budget-conscious | Lucid Origin / FLUX Dev / Phoenix 1.0 | All unlimited/free | Unlimited |
-
-### Model Capabilities Quick Reference
-| Model | Image Ref | Style Ref | Content Ref | Character Ref | Image-to-Image | Elements |
-|-------|-----------|-----------|-------------|---------------|----------------|----------|
-| Lucid Origin | — | Yes | Yes | — | — | — |
-| Lucid Realism | — | Yes | Yes | — | — | — |
-| FLUX Dev | — | Yes | Yes | — | — | Yes |
-| FLUX Schnell | — | Yes | Yes | — | — | — |
-| Phoenix 1.0 | — | Yes | Yes | Yes | Yes | — |
-| Phoenix 0.9 | — | Yes | Yes | Yes | Yes | — |
-| FLUX.2 Pro | — | — | — | — | — | Image Guidance |
-| Nano Banana 2 | Yes | — | — | — | — | — |
-| Seedream 4.5 | Yes | — | — | — | — | — |
-| GPT Image-1.5 | Yes | — | — | — | — | — |
-| Nano Banana Pro | Yes | — | — | — | — | — |
-| Ideogram 3.0 | — | — | — | — | — | — |
-
----
-
-## Video Models — Decision Matrix
-
-| Use Case | Best Model | Why | Cost |
-|----------|-----------|-----|------|
-| Quick testing / iteration | Motion 2.0 Fast | Fast, free, all controls | Unlimited |
-| Best free quality | Motion 2.0 | Higher quality, all controls | Unlimited |
-| Cinematic storytelling | Veo 3.1 | Start/end frame, audio | ~70 tokens |
-| Fast premium | Veo 3.1 Fast | Quick turnaround | ~35 tokens |
-| Realistic people & audio | Kling Video 3.0 | Longer videos, consistency | ~70 tokens |
-| Voiceovers & sound FX | Kling 2.6 | Natural voiceovers, audio | Paid |
-| Smooth cinematic | Sora 2 Pro | Refined detail, motion | ~70 tokens |
-| Social media (fast + free) | Motion 2.0 Fast | Speed + no cost | Unlimited |
-| Product showcase | Veo 3.1 Fast | Quick, professional | ~35 tokens |
-| Budget premium | LTX-2 Pro / Hailuo 2.3 | Quality per token | ~25 tokens |
-| Multi-instruction prompts | Kling O1 | Exceptional accuracy | Paid |
-| Image ref / start+end frame | Kling Video O3 Omni | Audio + image ref | Paid |
-| Basic subtle motion | Motion 1.0 | Simple image animation | Unlimited |
-
-### Video Model Capabilities
-| Model | Audio | Start Frame | End Frame | Image Ref | Controls | Elements | Styles | Fast |
-|-------|-------|-------------|-----------|-----------|----------|----------|--------|------|
-| Motion 2.0 | — | Yes | — | — | **Yes** | **Yes** | **Yes** | — |
-| Motion 2.0 Fast | — | Yes | — | — | **Yes** | **Yes** | **Yes** | Yes |
-| Motion 1.0 | — | Yes | — | — | — | — | — | — |
-| Kling Video 3.0 | Yes | Yes | Yes | — | — | — | — | — |
-| Kling Video O3 Omni | Yes | Yes | Yes | Yes | — | — | — | — |
-| Kling 2.6 | Yes | Yes | — | — | — | — | — | — |
-| Kling O1 | — | Yes | Yes | Yes | — | — | — | — |
-| Kling 2.5 Turbo | — | Yes | Yes | — | — | — | — | — |
-| Kling 2.5 Turbo Std | — | Yes | — | — | — | — | — | — |
-| Kling 2.1 Pro | — | Yes | Yes | — | — | — | — | — |
-| Veo 3.1 | Yes | Yes | Yes | Yes | — | — | — | — |
-| Veo 3.1 Fast | Yes | Yes | Yes | — | — | — | — | Yes |
-| Veo 3 | Yes | Yes | — | — | — | — | — | — |
-| Veo 3 Fast | Yes | Yes | — | — | — | — | — | Yes |
-| Sora 2 Pro | Yes | Yes | — | — | — | — | — | — |
-| Sora 2 | Yes | Yes | — | — | — | — | — | — |
-| Hailuo 2.3 | — | Yes | — | — | — | — | — | — |
-| Hailuo 2.3 Fast | — | Yes | — | — | — | — | — | — |
-| Seedance 1.0 Pro | — | Yes | Yes | — | — | — | — | — |
-| Seedance 1.0 Pro Fast | — | Yes | — | — | — | — | — | Yes |
-| Seedance 1.0 Lite | — | Yes | Yes | Yes | — | — | — | — |
-| LTX-2 Pro | Yes | Yes | — | — | — | — | — | — |
-| LTX-2 Fast | Yes | Yes | — | — | — | — | — | Yes |
-
-### Key Insight
-**Controls, Elements, and Styles are exclusive to Motion 2.0 / Motion 2.0 Fast.** All other models rely purely on prompt engineering for style and motion guidance.
-
----
-
-## Cost Optimization Tips
-
-1. **Start with Motion 2.0 Fast** for video iteration — it's free and unlimited
-2. **Use unlimited image models** (Lucid Origin, Lucid Realism, FLUX Dev, Phoenix) when experimenting
-3. **Switch to premium only for final renders** — Veo 3.1 Fast over Veo 3.1 saves ~50% tokens
-4. **Hailuo 2.3 and LTX-2 Pro** offer the best quality-per-token for premium video
-5. **Avoid 1080p unless necessary** — 720p is usually sufficient
-6. **Generate 1 at a time** to conserve tokens while iterating

package/skills/leonardo/modules/prompt-library.md

@@ -1,110 +0,0 @@
-# Prompt Library — Curated Templates
-
-Use these as foundations and adapt to the user's specific needs. All prompts follow Leonardo.ai best practices.
-
----
-
-## Video Prompt Templates
-
-### Cinematic / Film
-
-**Epic Establishing Shot**
-"Slow crane up over a vast mountain valley at dawn, morning mist pooling between dark pine ridges, the first golden light catching snow-capped peaks in the distance, a winding river reflects copper sky, the camera continues rising to reveal the endless landscape stretching to the horizon"
-
-**Character Introduction**
-"Dolly in toward a figure standing at the edge of a rain-soaked rooftop at night, city lights blurring into bokeh below, their coat collar turned up against the wind, neon signs reflecting in puddles at their feet, the camera pushes slowly to a medium close-up as they turn to face the lens"
-
-**Dramatic Reveal**
-"Super dolly in through a darkened corridor, light spilling from an opening ahead, dust particles floating in the beam, the camera accelerates as it reaches the threshold and bursts into a vast sunlit cathedral interior, stained glass casting prismatic light across stone columns"
-
-### Product / Commercial
-
-**Product Hero Shot**
-"Smooth orbit left around a matte black wireless speaker floating on a clean gradient background, studio rim lighting creating crisp edge highlights, subtle reflection on the surface below, the camera completes a quarter rotation revealing the speaker grille texture and LED indicator"
-
-**Lifestyle Integration**
-"Dolly right following a hand placing a ceramic coffee mug on a sunlit wooden table, steam rising from the surface catching golden morning light through linen curtains, shallow depth of field with a blurred kitchen garden visible through the window"
-
-### Nature / Landscape
-
-**Golden Hour Landscape**
-"Crane up over a field of wild lavender at sunset, wind creating rippling waves across the purple surface, a lone oak tree silhouetted against a gradient sky of amber and deep violet, fireflies beginning to emerge in the warm air, the camera rises to reveal rolling hills beyond"
-
-**Dramatic Weather**
-"Dolly in toward a lighthouse on a rocky cliff during a storm, massive waves crashing against dark basalt, spray exploding upward, the lighthouse beam cutting through sheets of rain, dark thunderclouds rolling overhead with distant lightning illuminating the churning sea"
-
-### Abstract / Artistic
-
-**Fluid Dynamics**
-"Macro dolly in on luminous ink drops falling into clear water in slow motion, magenta and gold pigment expanding in organic tendrils, light refracting through the mixing colors creating iridescent patterns, the camera pushes through the microscopic landscape of swirling fluid"
-
-**Geometric Transformation**
-"Orbit right around a cluster of floating metallic polyhedra catching studio light, each surface reflecting a different color, the shapes slowly rotate and reconfigure into new arrangements, sharp geometric edges creating precise shadow patterns on a matte white background"
-
-### Social Media / Short Form
-
-**Trending Hook**
-"Crash zoom in on a pair of hands unboxing a glossy product from minimalist packaging, tissue paper crinkling, the item emerges catching direct light, camera settles into a tight detail shot revealing the texture and craftsmanship, clean white background with soft shadows"
-
-**Satisfying Loop**
-"Top-down dolly in on a precise pour of thick caramel over a chocolate dessert, the golden liquid flowing in smooth ribbons, coating the surface and pooling at the edges, macro detail showing tiny air bubbles and glossy reflection, warm studio lighting"
-
----
-
-## Image Prompt Templates
-
-### Portrait / People
-
-**Editorial Portrait**
-"Editorial portrait of a woman in her 30s with natural curly hair, wearing a charcoal linen blazer against a blurred urban backdrop, shot at 85mm f/1.4 with soft window light from the left creating gentle catchlights, muted warm tones with shallow depth of field"
-
-**Character Concept**
-"Full-body character concept art of a cyberpunk street vendor, wearing a weathered leather jacket covered in holographic patches, neon-blue circuit tattoos visible on their neck, standing in a rain-slicked alley with steam vents, painted in a detailed digital art style with strong rim lighting"
-
-### Landscape / Architecture
-
-**Architectural Photography**
-"Interior of a minimalist concrete art gallery, double-height ceiling with a single rectangular skylight casting a blade of warm light across polished concrete floor, a single large-scale painting on the far wall, shot at 24mm with leading lines drawing the eye inward, muted gray and warm amber"
-
-**Fantasy Landscape**
-"Towering Gothic castle carved into a sea cliff face, waves crashing against dark volcanic rock below, twilight sky with scattered cirrus clouds catching the last amber light, ravens circling the highest tower, painted in the style of detailed fantasy concept art, deep blues and warm amber highlights"
-
-### Product
-
-**E-commerce Product Shot**
-"Pair of white minimalist sneakers on a clean light gray background, shot from 3/4 angle showing sole detail and stitching, crisp studio lighting with soft shadows, commercial photography style, neutral tones with bright white product pop"
-
-**Flat Lay**
-"Overhead flat lay of a curated workspace: leather-bound notebook, brass pen, ceramic espresso cup, succulent plant, and vintage brass compass arranged on weathered oak desk surface, soft diffused natural light from above, warm earth tones"
-
-### Logo / Design
-
-**Modern Logo**
-"Minimalist geometric logo design for a tech company, abstract interlocking shapes forming a stylized 'N', clean lines on white background, gradient from deep navy to electric blue, scalable vector aesthetic"
-
-**App Icon**
-"Rounded square app icon design, abstract sound wave visualization in gradient teal and purple, dark background, subtle glass reflection overlay, iOS design language, clean and recognizable at small sizes"
-
-### Illustration / Art
-
-**Fantasy Art**
-"Digital painting of a solitary astronaut standing on the surface of an alien world, a massive ringed planet dominating the sky above, bioluminescent flora glowing in soft greens and blues across the rocky terrain, painted with visible brushstrokes in the style of classic sci-fi illustration"
-
-**Sci-Fi Concept**
-"Interior of a derelict space station corridor, emergency lighting casting red-orange pools on the floor, overgrown with alien vegetation breaking through wall panels, a single shaft of white light from a hull breach, detailed concept art style with strong atmosphere and narrative tension"
-
----
-
-## Negative Prompt Templates
-
-### For Photorealistic Images
-"blurry, low quality, deformed, distorted, extra limbs, extra fingers, disfigured, bad anatomy, text, watermark, signature, cropped, out of frame, worst quality, jpeg artifacts"
-
-### For Illustration / Art
-"photographic, hyperrealistic, 3D render, stock photo, generic, clipart, low effort, blurry, text, watermark"
-
-### For Video (General)
-"blurry, low quality, distorted faces, text overlay, watermark, static image, frozen frame, glitch artifacts, unnatural motion, jittery, flickering"
-
-### For Product Shots
-"busy background, harsh shadows, unwanted reflections, text, hands, people, cluttered, low resolution, color cast"