Instructions to use SUSSYEATING/SDXL-Turbo-ConvRot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use SUSSYEATING/SDXL-Turbo-ConvRot with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
SDXL Turbo INT8 ConvRot for ComfyUI
Powered by Stability AI
Quantized single-file ComfyUI checkpoint derived from stabilityai/sdxl-turbo using ConvRot (block Hadamard rotation + row-wise symmetric INT8 quantization + calibration bias correction) while keeping the 80 most sensitive UNet linear layers preserved in FP16.
โ ๏ธ License Separation Notice: This model is hosted in a dedicated repository because it is governed by the Stability AI Community License Agreement rather than Open RAIL++-M or Apache-2.0. Please review the license terms below before commercial or downstream use.
Checkpoint Details
| File | Quantized Layers | File Size | Baseline FP16 Size | Reduction | Bias Corrections |
|---|---|---|---|---|---|
sdxl-turbo-1.0-int8-convrot.safetensors |
659 / 739 INT8 (80 protected FP16) | 5.18 GB | 6.94 GB | -25.3% | 256 linear biases |
- Drop straight into
ComfyUI/models/checkpoints/and load with the standardLoad Checkpointnode (ComfyUI >= v0.45.0). - Conv2d layers, text encoders (CLIP-L / OpenCLIP-G), and VAE remain unquantized.
Visual Comparisons (512ร512, 2 steps, SDTurboScheduler)
Evaluation Metrics (A100 GPU, ComfyUI v0.45.0, 24 Renders: 8 Prompts ร 3 Seeds)
Measured via scripts/verify_sdxl_quant.py at 512ร512, 2 steps, comparing directly against the unquantized FP16 checkpoint (sd_xl_turbo_1.0_fp16.safetensors), with unquantized BF16 (b_*) included as a baseline reference:
| Metric vs FP16 | INT8 ConvRot (659/739 INT8) | Unquantized BF16 Reference | Notes |
|---|---|---|---|
| Latent / Feature Cosine Mean | 0.99805 (min 0.98357) | 0.99802 (min 0.99386) | Higher mean than BF16 |
| SSIM Mean | 0.96659 (min 0.84238) | 0.92631 (min 0.88360) | +0.04028 higher mean SSIM than BF16 |
| PSNR Mean | 34.39 dB (min 26.97 dB) | 31.18 dB (min 27.16 dB) | +3.21 dB higher mean PSNR than BF16 |
| Warm Mean Time / Image | 0.69s | 0.22s | Hadamard dequant overhead traded for smaller size |
Full summary JSON: metrics/a100_turbo_int8_summary.json.
Stability AI Community License & Acceptable Use Policy
This model is a Derivative Work of stabilityai/sdxl-turbo and is distributed under the Stability AI Community License Agreement (sai-nc-community), Copyright ยฉ Stability AI Ltd. All Rights Reserved. See also the included NOTICE file.
Key terms under LICENSE.md:
- Research & Non-Commercial Use: Permitted royalty-free subject to Agreement terms and the Stability AI Acceptable Use Policy (AUP).
- Commercial Use (< $1M Annual Revenue): Permitted only if you register with Stability AI at https://stability.ai/community-license and you/your affiliates generate less than USD $1,000,000 in annual revenue. Entities above USD $1M require an Enterprise License from https://stability.ai/enterprise.
- Attribution: Downstream distributions must include
LICENSE.md,NOTICE, and prominently display Powered by Stability AI.
- Downloads last month
- 14
Model tree for SUSSYEATING/SDXL-Turbo-ConvRot
Base model
stabilityai/sdxl-turbo
