Voxel

Voxel ControlNet enables users to create or convert an existing model into a voxel representation, which can then be used to guide the overall shape and proportions of the new model. This is especially useful for maintaining specific body proportions or creating model variants while preserving the original structures.

Use Case

• Example: Generating a multi-head character (with exaggerated proportions) by using an existing multi-head model converted into voxels to guide the new model generation.

Example Representation

{
  "voxel_condition": "<Base64 Encoded Data>",
  "voxel_condition_cfg": true,
  "voxel_condition_weight": 1
}

• voxel_condition: A string containing Base64-encoded voxel data representing the 3D structure used as a condition for model generation.

• voxel_condition_cfg: A boolean value (true or false) that enables or disables the voxel condition guidance.

• voxel_condition_weight: A numerical value that determines the influence weight of the voxel condition on the generation process.

  • A higher weight increases the influence of the voxel condition, making the generated model more closely adhere to the provided voxel structure.

Voxel Condition Generation

Below is an explanation and a sample code snippet to illustrate the generation of voxel_condition.

Explanation

The voxel_condition is a Base64-encoded string that represents a 3D voxel structure. This voxel structure is used as a condition to guide the shape and proportions of the generated model. The process involves creating a 3D array of boolean values, encoding this array into a binary format, and then converting it to a Base64 string for use in the API.

Sample Code

Here's a Python code snippet that demonstrates how to generate the voxel_condition:

import numpy as np
import base64

# Generate a random 3D voxel array with fixed size (16x16x16)
voxel = np.random.choice([True, False], size=(16, 16, 16))

# Encode the voxel array into a Base64 string
voxel_condition = base64.b64encode(
    np.packbits(voxel, bitorder="little").tobytes()
).decode()

Here's a Python code snippet showing how you can validate the voxel generation:

import numpy as np
import base64

# Decode the Base64 string back to the original voxel array for verification
voxel_condition_parsed = np.unpackbits(
    np.frombuffer(base64.b64decode(voxel_condition.encode()), np.uint8), bitorder="little"
).astype(bool).reshape(16, 16, 16)

# Print the Base64-encoded voxel condition
print(voxel_condition)

# Verify that the original voxel array and the decoded voxel array are identical
assert np.all(voxel == voxel_condition_parsed)

---

For an example of a cURL request, please refer to the ControlNet Playground.

ControlNet Playground