Step 1: Open Realtime Canvas and Configure Style

Launch Leonardo AI and select the “Realtime Canvas” tab. Choose your target model — this determines the visual style applied to your sketches. If you’ve trained a custom Phoenix model, select it for brand-consistent output. Otherwise, pick a Leonardo model that matches your project’s aesthetic (e.g., “Anime” for character concepts, “3D Render” for game environments, “Sketch” for rough ideation). Set the creativity slider — lower values produce outputs closer to your sketch strokes; higher values give the AI more interpretive freedom.

Step 2: Set Up Your Canvas Workspace

Configure the canvas size and background. For character concepts, use a portrait-oriented canvas (800×1000px) with a neutral gray background. For environments, use landscape orientation (1200×800px) with a dark background that won’t interfere with generated lighting. Enable the “Instant Generation” toggle so images update as you draw rather than on-demand. This real-time feedback is the core of the workflow — you see results immediately, allowing continuous creative steering.

Step 3: Sketch and Steer in Real Time

Begin sketching your concept with rough strokes. Draw a character silhouette, an architectural outline, or a landscape horizon. As your strokes appear, the AI immediately transforms them into a styled rendering. Watch the output evolve as you add more detail. This is where the magic happens — you’re not waiting for generations, you’re painting with AI as your live collaborator. If the AI interprets your strokes differently than intended, adjust your drawing or modify the creativity slider to give more or less interpretive freedom.

Step 4: Refine with Selective Generation

When you’ve established a promising direction, switch from continuous real-time mode to selective generation. Highlight specific areas of your sketch (e.g., just the character’s face, just the building’s entrance) and generate refinements for those regions only. This selective approach lets you iterate on specific elements without disrupting the overall composition — far more efficient than regenerating the entire image each time you want to adjust one detail.

Step 5: Export and Continue in Your Pipeline

Once you’re satisfied with a concept direction, export the Realtime Canvas output as a high-resolution image. Import it into Photoshop, Procreate, or your preferred painting tool for manual refinement — adding details the AI missed, correcting anatomy, enhancing lighting. The Realtime Canvas output serves as a strong foundation that eliminates hours of initial sketching time, letting you focus your manual effort on the finishing touches that define professional concept art quality.

Step 1: Prepare Your Reference Dataset

Gather 10-50 high-quality images that exemplify your target visual style. For a brand, this might include existing marketing photography, product shots, and design mockups. For a game, collect concept art, character designs, and environment paintings. Quality matters more than quantity — every reference image should perfectly represent the style you want to replicate. Remove any outliers that deviate from your core aesthetic, as they’ll confuse the model.

Step 2: Create a New Phoenix Dataset

In Leonardo AI, navigate to the “Training” section and click “Create New Dataset.” Upload your reference images and assign descriptive tags to each one — not generic tags like “image” but specific ones like “dark fantasy castle, moody lighting, stone textures, atmospheric fog.” These tags teach the model what elements matter in your style. Tag quality directly impacts model quality, so be thorough and precise.

Step 3: Configure and Launch Training

Select your dataset and configure training parameters. Set the training strength (higher = closer to your reference style, lower = more creative freedom). Choose whether to enable style-only training (preserves composition flexibility) or full training (replicates both style and composition patterns). Click “Start Training” — the process typically takes 15-30 minutes. Leonardo will display progress updates and a quality score upon completion.

Step 4: Test Your Custom Model

Once training completes, your custom model appears in the model selector dropdown. Switch to it and generate several test images using prompts that describe scenes different from your reference set but in your trained style. For example, if your references were fantasy castles, prompt for a fantasy marketplace or a fantasy ship — different content, same style. Evaluate consistency across generations: do they all share the same color palette, lighting approach, texture detail, and overall mood? If results are inconsistent, add more reference images and retrain.

Step 5: Build Your Asset Library

With a validated custom model, start generating your full asset library. Create a prompt template system: “In [your trained model style], [scene description], [lighting], [composition].” Use this template for every generation to maintain maximum consistency. Save all outputs to your Leonardo project gallery, organized by category (characters, environments, items, UI elements). Export at your required resolution and format — Leonardo supports up to 4K output with transparent backgrounds for game sprites.

Step 1: Access 3D Texture Mode

Log into Leonardo AI and navigate to the 3D Texture generation tab. This mode is specifically designed for surface materials, not general images. It automatically tiles outputs, generates PBR maps, and controls material properties. Unlike the standard image generation mode, 3D Texture prioritizes surface realism over artistic composition — perfect for UV-mapped game assets.

Step 2: Describe Your Material in Detail

Write a material-focused prompt: “Seamless weathered stone brick wall texture, mortar gaps, moss patches, slightly damp, realistic outdoor masonry” or “Brushed aluminum metal texture, subtle scratches, industrial surface, high metalness.” Always include the word “seamless” and the material type (stone, metal, wood, fabric). Add weathering, color, and surface detail descriptors for realism. Avoid composition words like “landscape” or “character” — these confuse the texture model.

Step 3: Configure PBR Map Generation

Enable all PBR map outputs: Albedo (color), Normal (surface depth), Roughness (smoothness), and Metalness (reflectivity). Select the resolution matching your game’s texture budget — 1024×1024 for standard environments, 2048×2048 for hero assets. Leonardo generates all four maps simultaneously, ensuring they’re perfectly aligned — no manual alignment or separate generation needed.

Step 4: Generate and Inspect the Texture Tile

Click “Generate” and review the output in Leonardo’s preview panel. Check for visible seams at tile edges — zoom to the borders and verify the pattern repeats smoothly. If you see edge artifacts, adjust the prompt to emphasize “perfectly seamless tiling” and regenerate. The normal map should show subtle depth variation (not extreme bumps), and the roughness map should reflect your described surface properties.

Step 5: Fine-Tune with Property Controls

Leonardo‘s 3D Texture mode offers sliders for roughness, metalness, and detail intensity. After generating, adjust these sliders and regenerate to match your game’s rendering requirements. For a stylized game, reduce detail intensity and increase roughness uniformity. For a photorealistic game, maximize detail intensity and add fine scratch/dirt variation. Each adjustment produces new aligned PBR maps instantly.

Step 6: Export and Apply in Your Game Engine

Download all four PBR maps (Albedo, Normal, Roughness, Metalness) as separate PNG files. Import them into your game engine (Unity, Unreal, Godot) and assign each map to the corresponding material slot. Set the texture’s wrap mode to “Repeat” for seamless tiling. Test the material on a sample mesh in your scene — verify lighting response, surface detail, and seamless tiling at runtime. Build a Leonardo texture library by generating 20–30 common materials (stone, wood, metal, fabric variants) and organizing them in your engine’s asset folder.

Step 1: Define Your Character Design Brief

Before touching any AI tool, create a character design brief: name, personality, visual traits (hair color, eye shape, clothing style, body proportions), and reference art. Collect 10–20 images that represent your desired aesthetic — these could be from existing games, anime, or hand-drawn sketches. Upload these references to Leonardo AI’s Image Guidance section. This brief becomes your anchor for every generation.

Step 2: Choose and Configure the Right Model

Navigate to Leonardo AI‘s model selection panel. For stylized game characters, the Anime or Phoenix model works best. Select the model and set parameters: choose “Dynamic” generation quality for higher detail, set image dimensions to match your game’s sprite or portrait resolution (e.g., 512×512 for 2D, 1024×1024 for 3D renders), and adjust the “Prompt Magic” toggle to enhance prompt interpretation without over-stylizing.

Step 3: Craft Your Character Prompt with Consistency Anchors

Write a detailed prompt that includes all character traits from your brief: “A fierce warrior woman with silver braided hair, amber eyes, wearing dark leather armor with gold trim, holding a flame sword, standing in a dramatic pose against a stormy sky.” Always start with the character’s fixed traits (hair, eyes, clothing) before describing action or background. Use the same fixed trait description in every generation to maintain consistency.

Step 4: Use Image Guidance for Character Locking

Upload your best reference image or a previously generated character image to Leonardo’s Image Guidance. Set the “Strength” parameter to 0.5–0.7 — this balances creative variation with structural consistency. Higher strength locks the output closer to the reference; lower strength allows more creative interpretation. Generate variants (different poses, expressions, backgrounds) while keeping the character’s core appearance locked to your reference.

Step 5: Train a Personal Model for Long-Term Consistency

For projects requiring hundreds of consistent character images, train a custom model. Navigate to “Personal Models,” create a new dataset, and upload 30–50 images of your character across different angles, poses, and expressions. Click “Train Model” and wait 30–60 minutes. Once trained, select your personal model from the model dropdown and generate new character images that automatically match your trained style — no need for lengthy prompts or image guidance.

Step 6: Export and Organize Your Character Assets

Download generated images in PNG format with transparent backgrounds (enable “Remove Background” in post-processing). Organize assets in folders by character, pose type, and resolution. Create a naming convention (e.g., CharacterName_Pose_Background_Size.png) for efficient retrieval in your game engine. Leonardo AI’s batch generation feature lets you produce entire sprite sheets — generate 10 pose variations in one session, export, and compile them into your animation timeline.