sketch-to-multiview

SketchDream: Sketch-based Text-to-3D Generation and Editing

<!-- Provide a quick summary of what the model is/does. -->

Model Details

Input: sketch, depth maps, text input <br> Output: multi-view images of 3D models

Model Sources

<!-- Provide the basic links for the model. -->

For research purpose, we recommend our Github repository (https://github.com/IGLICT/SketchDream), <br> which includes detailed implementations.

• Repository: https://github.com/IGLICT/SketchDream
• Paper: https://arxiv.org/abs/2405.06461
• Project page: http://geometrylearning.com/SketchDream/

Uses

Feel free to use it under the Apache-2.0 license. Note that we don't have any official commercial product for ToonCrafter currently.

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> <!-- ### Direct Use We develop this repository for RESEARCH purposes, so it can only be used for personal/research/non-commercial purposes. -->

Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

• The generated videos are relatively short (2 seconds, FPS=8).
• The model cannot render legible text.
• The autoencoding part of the model is lossy, resulting in slight flickering artifacts.

How to Get Started with the Model

Check out https://github.com/IGLICT/SketchDream