README.md

---
license: other
pipeline_tag: text-to-image
tags:
- unet
- orbitquant
- quantization
- w4a4
- w3a4
- w2a4
- custom-runtime-required
- sdxl
---

# USE CONVROT INT4 and INT8 for now 

# OrbitQuant SDXL Exports

Experimental OrbitQuant and ConvRot quantized exports for CreaPrompt Lightning Hyper-SDXL.

> **Work in progress:** The native A4 runtime is not public yet. These models cannot currently be used without the custom runtime. A ComfyUI loader node that outputs a model compatible with the core KSampler is still under development.

## W2A4 Recovery Status

WIP for W2A4 block-level rollout recovery.

## Model Format

These are not standard SDXL checkpoints that can be loaded directly by existing SDXL loaders.

Depending on the export, the files can contain:

* OrbitQuant-packed SDXL UNet weights
* ConvRot-quantized SDXL UNet weights
* A4 activation-quantization metadata
* Quantized CLIP and text-encoder weights
* FP16 VAE weights
* `__orbitquant__` metadata
* Codebooks
* Rotations
* Quantization scales
* Runtime configuration

A custom runtime is required to execute the packed OrbitQuant and ConvRot weights without expanding them back into ordinary FP16 weights.

# Examples

## Full OrbitQuant versus Full ConvRot

<table>
  <tr>
    <td align="center">
      <img
        src="https://huggingface.co/ApacheOne/orbitquant_unets/resolve/main/hybrid_quants/orbitW4A4convrotW4A4quant/examples/comparisons/FULL_OQW4A4_vs_FULL_CRW4A4_CLIPINT4_comparison.png"
        width="760"
      >
      <br>
      <strong>Full OrbitQuant W4A4 versus Full ConvRot W4A4 — CLIP INT4</strong>
    </td>
  </tr>
</table>

## Full-UNet Tests

<table>
  <tr>
    <td align="center" width="50%">
      <img
        src="https://huggingface.co/ApacheOne/orbitquant_unets/resolve/main/hybrid_quants/orbitW4A4convrotW4A4quant/examples/full_unet/convrot_w4a4_clip_int4/FULLUNET_CRW4A4_CLIPINT4_test.png"
        width="420"
      >
      <br>
      <strong>Full ConvRot W4A4 UNet — CLIP INT4</strong>
    </td>
    <td align="center" width="50%">
      <img
        src="https://huggingface.co/ApacheOne/orbitquant_unets/resolve/main/hybrid_quants/orbitW4A4convrotW4A4quant/examples/full_unet/orbitquant_w4a4_clip_int4/FULLUNET_OQW4A4_CLIPINT4_test.png"
        width="420"
      >
      <br>
      <strong>Full OrbitQuant W4A4 UNet — CLIP INT4</strong>
    </td>
  </tr>
</table>

## Mixed OrbitQuant and ConvRot UNet — CLIP FP16

<table>
  <tr>
    <td align="center" width="50%">
      <img
        src="https://huggingface.co/ApacheOne/orbitquant_unets/resolve/main/hybrid_quants/orbitW4A4convrotW4A4quant/examples/mixed_unet/clip_fp16/creaprompt_SDXL_OQW4A4_CRW4A4_CLIPFP16_test.png"
        width="420"
      >
      <br>
      <strong>OrbitQuant W4A4 + ConvRot W4A4 — CLIP FP16</strong>
    </td>
    <td align="center" width="50%">
      <img
        src="https://huggingface.co/ApacheOne/orbitquant_unets/resolve/main/hybrid_quants/orbitW4A4convrotW4A4quant/examples/mixed_unet/clip_fp16/creaprompt_SDXL_OQW4A4_CRW8A8_CLIPFP16_test.png"
        width="420"
      >
      <br>
      <strong>OrbitQuant W4A4 + ConvRot W8A8 — CLIP FP16</strong>
    </td>
  </tr>
</table>

## Mixed OrbitQuant and ConvRot UNet — CLIP INT4

<table>
  <tr>
    <td align="center" width="50%">
      <img
        src="https://huggingface.co/ApacheOne/orbitquant_unets/resolve/main/hybrid_quants/orbitW4A4convrotW4A4quant/examples/mixed_unet/clip_int4/creaprompt_SDXL_OQW4A4_CRW4A4_CLIPINT4_test.png"
        width="420"
      >
      <br>
      <strong>OrbitQuant W4A4 + ConvRot W4A4 — CLIP INT4</strong>
    </td>
    <td align="center" width="50%">
      <img
        src="https://huggingface.co/ApacheOne/orbitquant_unets/resolve/main/hybrid_quants/orbitW4A4convrotW4A4quant/examples/mixed_unet/clip_int4/creaprompt_SDXL_OQW4A4_CRW8A8_CLIPINT4_test.png"
        width="420"
      >
      <br>
      <strong>OrbitQuant W4A4 + ConvRot W8A8 — CLIP INT4</strong>
    </td>
  </tr>
</table>

## Mixed OrbitQuant and ConvRot UNet — CLIP INT8

<table>
  <tr>
    <td align="center" width="50%">
      <img
        src="https://huggingface.co/ApacheOne/orbitquant_unets/resolve/main/hybrid_quants/orbitW4A4convrotW4A4quant/examples/mixed_unet/clip_int8/creaprompt_OQW4A4_CRW8A8_test.png"
        width="420"
      >
      <br>
      <strong>OrbitQuant W4A4 + ConvRot W8A8 — CLIP INT8</strong>
    </td>
    <td align="center" width="50%">
      <img
        src="https://huggingface.co/ApacheOne/orbitquant_unets/resolve/main/hybrid_quants/orbitW4A4convrotW4A4quant/examples/mixed_unet/clip_int8/first_model_test.png"
        width="420"
      >
      <br>
      <strong>First Mixed-Quant Model Test — CLIP INT8</strong>
    </td>
  </tr>
</table>

## Root Example

<table>
  <tr>
    <td align="center">
      <img
        src="https://huggingface.co/ApacheOne/orbitquant_unets/resolve/main/hybrid_quants/orbitW4A4convrotW4A4quant/examples/creaprompt_SDXL_OQW4A4_CRW8A8_CLIPINT4_test.png"
        width="520"
      >
      <br>
      <strong>OrbitQuant W4A4 + ConvRot W8A8 — CLIP INT4</strong>
    </td>
  </tr>
</table>

## Runtime Availability

The following components are still required for normal use:

* Native packed OrbitQuant weight execution
* Native A4 activation quantization
* Native ConvRot quantized operators
* ComfyUI model loader
* Integration with the core ComfyUI KSampler
* Runtime validation
* Performance tuning

Until the custom runtime is released, these files should be considered experimental development exports.