1 of 4

FAQ

Can I animate my generated models?

Yes! Models that are created using our Generate Anything tool can then be animated using our Animate Anything tool. Keep in mind however, that the model needs to fit into our supported categories in order to successfully receive a rig and animations.

What format will my generated model be in?

Generated models are provided in the following formats: FBX, GLB, GLTF, OBJ & USDZ Downloads include both the mesh and texture of the model.

Can I edit my generated models?

Absolutely! Generated Models can be downloaded as-is and can be opened in 3D editing software to make any adjustments you like.

Expected Results by Category

Here you can get a general idea of how our tool currently responds to the most commonly used text prompts and image examples and what quality of model you can expect.

Please refer to this table for our current expectations of model generation from our Generate Anything tool by category, as well as whether or not that category can then be animated using our Animate Anything tools.

Be aware that this table references the reliability of the generation, and not the quality of the textures produced, which may vary.

Please note, our Generate Anything tool is in the Early Access stage and outliers may occur in generations of any type. This table is to be used as a general guide and is by no means exhaustive or definitive.

Result Key - High: regularly good results | Average: mostly good results | Low: unpredictable results

Best Practices for Best Results

Here you can find information on how best to use our Generate Anything tool to ensure you get the best possible results for your model generation, whether you choose to use image or text generation.

Best Practices for: Image to 3D Model Generation

Images with busy backgrounds may cause issues with generation, including but not limited to unwanted textures and mesh misshaping. To avoid this, it is best to remove all backgrounds and keep the image focus entirely on the subject for your model.

Additionally, try to avoid having more than one subject in the image, otherwise the tool may not be able to determine which source to use for the model.

Try your best to ensure the source for the model in your image has all limbs visibly separated in some way (e.g. gaps between legs, arms) to ensure a clean, concise generation.

Higher resolution images may take a little longer to generate but will likely provide higher texture quality on the finished model.

If you are unable to separate your model source from the background, it is best that the background and subject have a contrast between them to help determine the model source. This can be done by having a bright background, or by increasing the intensity of colour, sharpness and detail of the model in the image.

Remember to consider that when using an image with a background there is always a chance that some of the background image may leak into the final texture, or some mesh irregularities may occur, especially in cases where the model source and background have similar colours.

Be wary of artifacts in your images, especially in white or empty space, and these may create anomalies in your model generation.

Best practices for: Text to 3D Model Generation

Ensure your text prompts are clear and concise. Spelling errors may cause issues with generation, so be sure to proof read your prompt before generation.

When writing your text prompts, the level of detail matters depending on what you're after. For example, if you're looking for a generic cat model, you can simply use the prompt "cat". However, if you require specific details, you can include this in the prompt - for example "cat with a fluffy tail" would be some slight further detail specific to your generation.

You can take this further by being more precise, although generations with excessive detail may vary in quality depending on the category. Another example would be "pink cat with tiger print fur" which contains much more precise detail.

Colours can also be defined using text prompts, and this can also create variations in the result depending on the detail used. Using more precise colour specifics ("dark blue" "light blue") can be helpful, but general colours are likely to yield better results. Note that hex colour codes will not work.

Some 'aesthetics' may be used in text prompts (e.g. cyberpunk, vaporwave, grunge) however these are not always guaranteed to be picked up by the system or may provide varying results, and are much less reliable that using colour terms.

Best practices for: Animating your Generated models

Generating models you want to animate with Animate Anything? Here are some tips to help ensure your model will meet the constraints of the Animate Anything system.

Make sure your model's category is supported by Animate Anything, you can find this out by referencing this table.

For all models, you need to ensure they still meet the constraints of our systems. For text prompt generated models, it can be useful to include the term 'symmetrical' (or just keeping the prompt refinement checkbox ticked) and for image generated models, having a subject with a visibly symmetrical shape can be helpful.

For biped human and humanoid models, the pose can be really important. We recommend generated models aim for an A-pose for these categories.

If you're using Text-To-3D, you can select the optional prompt refinement checkbox to default to an A-pose for your model when generating humans and humanoids.

For further information on preparing a model for Animate Anything, you can take a look at our other documentation.

Generate Anything Quickstart

This guide will explain each step of the Generate Anything processes.

The Generate Anything service is currently in an early access stage, so whilst Generate Anything is in these earlier stages, please bear with us! Before anything else, you need to started by opening Animate Anything website and signing in or signing up.

Next, you have to decide if you want to create a model using either our Image to 3D tool, or out Text to 3D tool. To begin with, we'll take a look at Image to 3D, but go ahead and scroll ahead if you're looking for Text to 3D instead.

Image to 3D Model Generation

Firstly, navigate to Generate Anything, which can be found on the top right of the Anything World toolbar.

On the Generate Anything homepage, select "Create from image" (right-hand button)

Either Drag and drop your image file or click "Browse your files" to navigate to the image file you want to use. Remember to refer to our Best Practices for Best Results page before uploading so you can properly prepare your image for the best outcome.

You can then add a Model Name in the provided text box, however this is optional. The mandatory checkbox confirms you have read and accepted our system constraints, as well as the terms of use of the tool.

Image-To-3D constraints are as follows:

Use a transparent background or a single-coloured one.
Feature just one object, creature or character in the image. You should avoid even floor elements, and shadows on the floor or background.
The image should be moderately illuminated. Avoid excessive occlusion or extreme shininess.
Creatures or characters in images should display all their limbs clearly and follow conventional poses, ideally symmetrical. Otherwise, it is more likely to get an unexpected number of limbs in the model or other defects.
The image should be of high quality, avoiding blurriness, noise, text and other watermarks. Even in those conditions, please note that the system is not perfect and fine-grained details such as fingers, face details or accessories may not have outstanding quality.
Use JPG, JPEG or PNG images. If you are prompted that the image exceeds the file size limit, try reducing the resolution or modifying compression settings.

When you're ready to proceed, press Generate.

After pressing Generate, you will be taken to the generation progress screen, which shows you the status of your generation. This process can take up to six minutes.

Once your model has finished processing, you will be presented with the finished generation.

From here, you can choose to download the model as-is, generate another model, or go ahead and animate the model using our Animate Anything tool. Your generated model will also be avaliable to view in My World, under generated models, so you can access it any time!

Text to 3D Model Generation

If you haven't already, navigate to Generate Anything, which can be found on the top right of the Anything World toolbar.

On the Generate Anything homepage, select "Create from Text prompt" (left-hand button)

Write your text prompt into the provided text box, then select the appropriate checkboxes.

The Optional checkbox provides an option to generate your model with a standard pose that would be best suited for animation, should you want to use this. If you have a particular pose in mind for your prompt, it is recommended that you keep this unchecked.

The mandatory checkbox confirms you have read and accepted our system constraints, as well as the terms of use of the tool.

Text-To-3D Constraints are as follows:

Describe a single object, creature or character in a noun phrase, adding only the adjectives you consider necessary, for example “blue cat” or “monkey with elephant head”.
Avoid over-complicating the prompt: if there are multiple ways of expressing your idea, use the simpler one. For example, “yellow submarine” is simpler than “submarine painted in yellow” or “submarine, yellow”.
Avoid non-English or very uncommon words, accents or other symbols when possible. Support for additional languages may come in the future.
Limit your text prompt to 100 characters.

When you're ready, hit Generate.

After pressing Generate, you will be taken to the generation progress screen, which shows you the status of your generation. This process can take up to six minutes.

Once your model has finished processing, you will be presented with the finished generation.

You can now decided to download the model as-is, generate another model, or animate the model using our Animate Anything tool. Your generated model will also be available to view in My World, under generated models, so you can access it any time!

Finding Your Models in My World

You can find all your successfully generated models in My World. To access this area, either select 'My World' from the dropdown menu when you hover over your profile image in the top right of the web application, or alternatively you can select 'My World' from the navigation on the left whilst on your personal Dashboard.

Once you navigate to My World, you can view your generated models by selecting the option 'Generated Models'. This will show you a truncated selection of your generated models. In order to view all models, be sure to select 'View All' on the right-hand side of the screen.

You can tell which method was used to generate a model by referring to the icon on the top-left of the thumbnail.

From the generated models screen, you can either select the model by clicking the thumbnail to be taken to the model viewer, where you can download your model, or you can press the 'Animate' button to be taken directly to the Animate Anything interface and start the process of animating the selected model.

Downloading & Animating Your Model

On the Model Viewer Screen you will be able to download your generated model. You can do this by pressing the button marked 'Download'

Generated Models can be downloaded in the following formats:

FBX, GLB, GLTF, OBJ & USDZ

If you wish to animate your model using our Animate Anything tool, all you need to do is press the button marked 'Animate Model' which will lead you through the Animate Anything interface. For further information on this process, please refer to our documentation here.