You've got questions? We've got answers!
Explore our comprehensive documentation for in-depth information about Ludo.ai and its powerful features.3D Asset Generator
Introduction
The 3D Generator is a powerful tool within the Ludo.ai platform that allows you to create 3D assets for your games using text prompts, images, or a combination of both. It leverages advanced AI to generate models quickly and efficiently, streamlining your asset creation workflow.
Key Features:
- Text-to-3D: Create models directly from descriptive text prompts.
- Image-to-3D: Transform 2D images into 3D models.
- Texture Generation: Add textures to your own models or change the texture of previously generated models.
- Model Variation: Generate variations of your own models or previously generated models.
- Multiple 3D Model Views: View textured and untextured (mesh) versions of your generated models.
- Iterative Refinement: Generate variations and refine results through textual prompts.
- Download Options: Download models in various formats (GLB, STL, PLY, OBJ, OFF).
- Favorites System: Save your best creations for easy access.
- In-Platform Image Editor: Modify your input images before 3D transformation (accessible via "Open in Editor").
Getting Started
- Access the 3D Generator: Log into your Ludo.ai account and select "3D Asset Generator" from the main menu.
- Choose a Generation Mode: Select the tab for the type of generation you want to use: "Text to 3D", "Image to 3D", "Texture Generation" or "Model Variation".
- Provide Input:
- Text to 3D: Enter a text description of the 3D model you want to create.
- Image to 3D: Click "Choose reference image" and upload or choose an image. For best results, use a clear image of a single subject.
- Texture Generation: Select the model you would like to apply a texture on, and describe the texture.
- Model Variation: Select the model that you would like to edit. Then provide in the text box, a description on how you want to change it.
- Click "Generate": Ludo.ai will process your input and create the 3D model.
- View, Refine, and Download: See next sections.
Text-to-3D
This mode creates a 3D model based solely on your text input. The more detailed and descriptive your text, the better and more relevant the results will be. The AI interprets your description and generates a 2D image representation, which is then used to create the 3D model.
How to Use
- Select the "Text to 3D" tab.
- Enter your text prompt in the input box. Be as specific as possible.
- Click "Generate".
- Ludo.ai will generate a 2D preview image. If needed, iterate using "Generate" again.
- Once satisfied, select the "Generate 3D object" to convert the image into a 3D model.
- View, refine, retry, or export the results.
Example Prompts
- "A low-poly, cartoonish treasure chest with gold trim and a skull emblem."
- "A futuristic spaceship with glowing blue engines and a sleek, metallic hull."
- "A black cartoon lego stormtrooper"
- "A whimsical mushroom house with glowing windows."
Tips
- The prompt should focus on a single subject. The generator cannot generate scenes or environments.
- Use adjectives to describe the desired shape, color, material, style, and any specific features. For example, instead of "sword," try "ornate elven sword with a glowing blue blade and a golden hilt."
- Experiment with different wording. Rephrasing or adding/removing keywords can significantly impact results.
Image-to-3D
This mode uses a 2D image as the primary input for creating a 3D model. The AI analyzes the image and attempts to extrapolate its 3D form, removing the background.
How to Use
- Select the "Image to 3D" tab.
- Click "Choose reference image" and upload a 2D image from your computer or choose one your favorites in Ludo.
- (Optional) Click "Open in Editor" to make adjustments to the image before generating the 3D model. You can use the masking tool and text prompts to guide the AI's edits.
- Click "Generate".
- Ludo.ai will process the input image, remove the background, and then generate a 3D model based on it.
- View, refine, retry, or export the 3D model.
Best Practices
- Use images with a single, clearly defined subject. The object should be fully visible.
- The subject can be over a background (it will be automatically removed), but there should be a clear distinction between subject and background.
- The AI will not be able to process images of scenes or environments, and the results will be unpredictable.
- Your uploaded images should have a resolution of at least 512x512.
- Use the "Open in Editor" to remove or change unwanted elements before generating.
Texture Generation and Model Variations
Using these two generation modes, you are able to upload your own 3D assets, or choose one of the previously generated assets, to create variations. See the section below to learn the restrictions on the models that can be uploaded, and how to prepare them for upload.
Texture Generation
This mode allows you to apply new textures to an existing 3D model. The mesh of the original model will not be modified.
How to Use:
- Select the "Texture Generation" tab.
- Click on the "Choose reference model" to choose a 3D model, either uploaded (see notes above) or a previous generation.
- Enter a text prompt describing the desired texture in the "Describe the model texture here" box.
- Note that the texture of the input model (if any) will be ignored. Your prompt should describe the new texture, not texture modifications.
- Click "Generate".
- Ludo.ai will generate a new 3D model, keeping the original mesh but with the new texture.
Tips:
- If your description simultaneously describes the asset and it's texture, the results are more likely to be accurate.
- Ex: "cartoonish dinosaur with purple and green skin"
- But if you only describe the texture it should still produce good results for most assets.
- Ex: "purple and green skin"
- Be as specific, use adjectives to define color, material, style.
Model Variation
This mode allows you to generate variations of an existing 3D model, making subtle or significant changes based on text prompts and strength sliders.
How to Use:
- Click the "Model Variation" tab.
- Click on the "Choose reference model" to choose a 3D model, either uploaded (see notes above) or a previous generation.
- Enter a text prompt in the box to describe the desired changes. For example: "make it more evil".
- Adjust the "Mesh Strength" and "Texture Strength" sliders:
- Mesh Strength: Controls how much the 3D geometry (shape) is allowed to change. 0% allows for significant changes, while 100% attempts to preserve the original shape.
- Texture Strength: Controls how much the original texture is preserved. 0% allows for significant texture changes, while 100% attempts to keep the original texture. Important: this slider will not be available for uploaded assets due to limitations in rendering user-uploaded models.
- Click "Generate."
Tips:
- The prompts can target shape modifications, texture modifications, or both. The effect will also depend on the Mesh and Texture strength sliders.
- If you are not seeing any significant changes, lower the strength sliders.
- If the reference (input) model is an uploaded model, the texture will always be generated from scratch, and the original texture will be ignored.
How to Upload 3D Models
The Texture Generation and Model Variation modes allow you to uploaded your own 3D assets for modification.
The uploaded 3D files should contain a single subject. 3D files with multiple models or scenes will produce unexpected and low-quality results.
Limitations
We have the following restrictions on the 3D models that can be uploaded:
- Must be one of the following file types: obj, ply, stl, 3ds, gltf, glb, fbx, off, dae, ctm, x3d
- The file should only contain the subject 3D model and nothing else.
- Although there are no hard limits, the meshes should have less than 100k vertices.
- Maximum file size: 20MB.
Preparing the model for upload with Blender
Blender can be used to reliably export the model to a supported format:
- Open the Blender file or import into your model into Blender.
File > Open
orFile > Import > ...
- Using the editor, delete any undesirable objects from the file, keeping only the main subject.
- Export the model to glTF
File > Export > glTF 2.0 (.glb/.gltf)
- In the export options:
Include > Limit to > Renderable Objects
☑️Transform > +Y Up transform
☑️Data > Material > Materials > No export
Data > Shape Keys
: ☐ DisableData > Skinning
: ☐ DisableData > Compression
: ☐ DisableAnimation
: ☐ Disable
- Select the file path and click on the export button.
Viewing and Interacting with Results
After generating a 3D model, it will appear in the results area with several interaction options:
- 3D Model Preview: A rotating video of the rendered generated asset.
- 2D Image: The image that was used as a basis for the 3D model creation.
- View Options (Toggle): Located above the 3D model preview.
- Switch to Standard View: Displays the model with textures and colors applied (the default view).
- Switch to Mesh View: Shows the normal map of the mesh of the model. This is useful for examining the model's topology.
- Download (Down Arrow): Downloads the current 3D model in your chosen format (GLB, STL, PLY, OBJ, OFF).
- Add to Favorites (Heart): Saves the current model to your Ludo.ai Favorites.
- Contextual generation options (...): Provides options to generate new assets based on the selected asset:
- Edit base image: Sends the model to the Image-to-3D tab, where you'll be able to edit the base image by clicking on "Open in Editor"
- Retry 3D model generation: Create a new 3D model using exactly the same inputs and base image. Allows you to retry the generation.
- Re-texture: Opens the Texture Generation mode with the current model pre-selected.
- Generate variations: Opens the Model Variation mode with the current model pre-selected.
Downloading Models
Ludo.ai's 3D Generator allows you to download your generated models in several popular 3D file formats:
- GLB: A binary format for glTF (GL Transmission Format) that includes textures. This is the recommended format for general use, as it preserves both the model's geometry and its visual appearance. This is the only format that will have textures applied.
- STL: A common format for 3D printing, containing only surface geometry (no color or texture information). Use this format if you plan to 3D print your model.
- PLY: A flexible format that can store color and other data per vertex. It's often used for 3D scanned data.
- OBJ: A widely supported format for representing 3D geometry. It can store some material information but is generally less comprehensive than GLB for textured models.
- OFF: A simple text-based format for describing polyhedral objects. It's primarily used for geometric modeling and does not support textures.
Important Note: Only the GLB format will include the textures you see in the textured preview. Other formats will export only the mesh (the shape of the model without colors or textures).
When choosing a format, consider the following:
- For use in game engines or 3D software: GLB is generally the best choice if you need textures.
- For 3D printing: STL is the most widely accepted format.
- For specific applications: Some software may have preferences for PLY, OBJ, or OFF.
Note: To directly import GLB files into Unity you will likely need to instal the Unity glTFast package found here: https://docs.unity3d.com/Packages/com.unity.cloud.gltfast@6.10
Tips for Effective 3D Generation
Be Descriptive: The AI thrives on detail. The more specific you are in your text prompt, the better the AI can understand your vision. Use adjectives to describe the desired shape, style, color, material, and any other relevant characteristics.
- Example: Instead of "sword," try "ornate elven sword with a glowing blue blade and a golden hilt."
Experiment with Different Prompts: Don't be afraid to try variations of your prompt. Sometimes, rephrasing or adding/removing keywords can significantly improve the results.
- Example: If "futuristic sports car" isn't giving you what you want, try "sleek, low-poly sports car with neon lights and large spoiler."
Use Reference Images: When you have a specific design in mind, providing a reference image can significantly improve the results. The AI can use this image as a visual guide to better understand your desired aesthetic. The image should clearly show a single subject for best results.
Iterate and Refine: The "Generate More" and "Generate New 3D Object" features are your friends. Use them to create variations and gradually refine the model towards your desired outcome. Each iteration can build upon the previous one, allowing you to fine-tune the results.
Combine Text and Image Inputs: For complex concepts, combining a descriptive prompt with a relevant image can yield the most accurate results. The text can provide context and details, while the image serves as a visual anchor.
- Example: Upload an image of a basic car shape and use the prompt "transform into a rusty, post-apocalyptic war machine with spikes and armor plates."
Understand the Limitations: The AI is a powerful tool, but it's not magic. It may sometimes misinterpret prompts or produce unexpected results. Be prepared to iterate and guide the process. Also, remember that very complex or abstract concepts might be challenging for the AI to grasp fully.
Consider the Different Download Formats: Choose the format that best suits your intended use. Remember that only GLB files will include textures, while other formats export only the mesh.
Troubleshooting
Model not generating:
- Check your internet connection: Ensure you have a stable internet connection, as the 3D Generator requires it to function.
- Try again: Try generating again with the same inputs.
Errors with uploaded models:
- There are limitations around the models you can upload to Ludo. Try preparing/exporting your model before upload using Blender, as described in "How to Upload 3D Models".
Results are not what you expected:
- Rephrase your prompt: Try different wording, add more descriptive details, or be more specific about certain aspects.
- Use a reference image: If you have a particular design in mind, provide a visual reference for the AI.
- Iterate: Use the "Generate More" or "Generate New 3D Object" features to explore variations and refine the model.
Slow generation times:
- Server load: High server traffic can sometimes lead to slower generation times. Try generating during off-peak hours if you experience consistent slowdowns.
Download issues:
- Storage space: Ensure you have sufficient storage space on your device to save the downloaded model.
- Browser settings: Check your browser settings to make sure downloads are allowed and that you know where downloaded files are saved.
- Download taking too long: Model export can take some time until the model starts to download. Wait at least 1 minute.
Unexpected errors:
- Refresh the page: Sometimes a simple page refresh can resolve minor glitches.
- Log out and back in: If refreshing doesn't work, try logging out of your Ludo.ai account and then logging back in.
- Contact support: If you encounter persistent errors, contact Ludo.ai support with details about the issue, including your prompt, any error messages you received, and the steps you've already taken.
Use Cases in Game Development
- Rapid Prototyping: Quickly create placeholder 3D assets to test gameplay mechanics, level layouts, or overall game feel without investing significant time in detailed modeling.
- Concept Visualization: Bring your game ideas to life in 3D early in the development process. This helps visualize the game's aesthetic and can be used for pitching or team communication.
- Asset Customization: Generate variations of existing assets to add diversity to your game world. For example, you could create multiple versions of a base character model with different clothing, accessories, or color schemes.
- Inspiration and Exploration: Experiment with different styles, themes, and concepts to spark new ideas and push creative boundaries. The 3D Generator can be a powerful tool for brainstorming and exploring uncharted territory.
- Character and Object Design: Create unique characters, creatures, props, and environmental elements. The AI can generate designs that you might not have considered otherwise.
- Level Design: Generate 3D models of buildings, structures, or natural formations to populate your game environments. This can be especially helpful for quickly blocking out levels or creating variations of environment assets.
Best Practices
- Start Simple, Then Add Detail: Begin with a basic description of your desired object and gradually add more details as you refine the model through iterations. This approach allows the AI to establish a solid foundation before incorporating finer details.
- Use Clear and Concise Language: Avoid overly complex sentences or technical jargon that the AI might not understand. Use straightforward language to describe the object's appearance, style, and any specific features.
- Focus on One Object at a Time: The 3D Generator works best when generating a single object or asset. If you need multiple objects, generate them separately and then combine them in your game engine or 3D modeling software.
- Consider Your Target Platform: Keep in mind the technical limitations of your target platform (e.g., polygon count, texture resolution) when creating 3D models. The 3D Generator can create highly detailed models, but you may need to optimize them further for performance in your game.
- Save Your Work: Add your favorite generations to your Favorites so you can easily access, reuse, or further refine them later. This also helps you keep track of your best creations.
- Combine with Other Ludo.ai Tools: Use the 3D Generator in conjunction with other tools like the Game Ideator and Game Concept to create a comprehensive and well-developed game concept. You can, for instance, generate a game idea, develop it into a concept, and then use the 3D Generator to create assets for it.
Image Editing with the Integrated Image Editor
Before generating 3D models from images, you can refine your 2D input using Ludo.ai's integrated Image Editor. This powerful tool allows you to make precise adjustments to your images, ensuring they are optimized for the 3D generation process.
Accessing the Image Editor
Upload an Image: In the 3D Generator, select the Image-to-3D tab and then click on "Choose reference image" and upload your desired image.
Open in Editor: Once the image is uploaded, click on the "Open in Editor" button located next to the image preview.
Image Editor Features
The Image Editor provides a user-friendly interface with the following features:
Masking Tool
- Brush Tool: Use the brush tool to paint over the areas of the image you want to modify. You can adjust the brush size using the slider.
- Undo/Redo: Correct any mistakes easily with the "Undo" and "Redo" buttons.
- Reset: Clears the entire mask, allowing you to start over.
Prompt Input
- Description Box: Describe the changes you want to make to the masked region of your image, or to the entire image if no mask is used. Be as specific as possible to guide the AI.
- Example: "add horns", "make the background a forest"
- Image Strength
- Slider: This slider controls the intensity of the changes applied to the image.
- 0: The AI will make significant changes, potentially altering the original image considerably.
- 100: The AI will make subtle changes, closely adhering to the original image's structure and style.
Editing Modes
- Edit: (Default mode) In this mode, you can add or change elements in the image. Use prompts in the description box to specify the modifications you want to apply, and use masks to restrict the edits to specific regions.
- Remove: This mode is designed for object removal.
- Select the "Remove" mode in the Image Editor.
- Use the brush tool to paint a mask over the object you want to remove.
- Click "Generate". The AI will attempt to remove the masked object and fill the area contextually.
Editing History
- Image Thumbnails: The right side of the editor displays a history of your edits. Click on any thumbnail to revert to a previous state.
Editing Workflow
- Select areas to edit: Use the brush tool to mask the specific parts of the image you want to modify (optional, for targeted edits).
- Choose Editing Mode: Select 'Edit' to add or change elements, or 'Remove' to erase objects.
- Describe the changes: In the "Description Box", write a clear and concise prompt explaining the desired modifications. Leave empty for 'Retouch' mode.
- Adjust Image Strength: Use the slider to set the intensity of the changes.
- Generate: Click the "Generate" button to apply the edits.
- Iterate: Review the changes and make further adjustments as needed. You can always revert to previous versions using the editing history.
Tips for Effective Image Editing
- Be precise with masking: Carefully outline the areas you want to change to ensure accurate edits, especially for object removal or targeted modifications.
- Use specific prompts: The more detailed your description, the better the AI will understand your intentions.
- Experiment with image strength: Try different values to find the right balance between preserving the original image and applying your modifications. Lower strength values are better for large modifications, and higher values for subtle edits.
- Utilize the editing history: Don't be afraid to experiment. You can always revert to earlier versions if needed.
3D Asset Generation in the Chat Assistant
In addition to the dedicated 3D Generator tool, you can also create 3D models directly within Ludo.ai's Chat Assistant, both the standalone version and the "Ask Ludo" version integrated into the Game Concept tool. This feature allows for a more conversational and interactive way to generate assets, fitting seamlessly into your brainstorming and development workflow.
How to Use It:
- Access the Chat Assistant:
- Standalone Chat Assistant: Click the chat bubble icon in the main menu to open the standalone Chat Assistant.
- "Ask Ludo" in Game Concept: Within a Game Concept document, click the "Ask Ludo" button at the top or within specific sections to access the context-aware assistant.
- Make Your Request: Type a natural language request for the 3D model you want to generate. Be as descriptive as possible.
- Examples:
- "Generate a 3D model of a wooden treasure chest."
- "I need a 3D asset of a futuristic motorcycle."
- "Create a low-poly 3D model of a fantasy character."
- Examples:
- Generate and Refine: The AI will process your request and generate a 3D model, which will appear directly in the chat. You can then:
- Iterate: Ask for variations or modifications using follow-up prompts.
- Download: Download the model in your preferred format (GLB, STL, PLY, OBJ, OFF).
- Add to Favorites: Save the model to your Favorites library.
Tips for Best Results:
- Be Specific: Just like with the dedicated 3D Generator, the more details you provide in your request, the better the results will be.
- Use Follow-Up Prompts: Refine your generated model by asking for specific changes or variations.
- Leverage Context (in Game Concept): When using "Ask Ludo" within a Game Concept, the AI will consider the existing content of your document, providing more relevant suggestions.
- Combine with Other Tools: Use the Chat Assistant to quickly generate an asset and then further refine it in the dedicated 3D Generator tool if needed.
Benefits of Using the Chat Assistant for 3D Generation:
- Conversational Workflow: Generate assets naturally as part of a broader conversation about your game.
- Idea Expansion: Quickly explore different asset ideas without leaving your current workflow.
- Contextual Awareness (in Game Concept): Get suggestions that are tailored to your specific game concept.
- Streamlined Process: Generate, refine, and save 3D models all within the chat interface.
- Access the Chat Assistant: