---
license: apache-2.0
base_model: ChenDY/NitroFusion2
base_model_relation: quantized
pipeline_tag: text-to-image
tags:
  - comfyui
  - nitrofusion2
  - z-image-turbo
  - one-step
  - few-step
  - int8
  - w6a8
  - w4a8
  - gptq
  - quantized
---

# NitroFusion2 for ComfyUI: int8, W6A8, W4A8

**[NitroFusion2](https://huggingface.co/ChenDY/NitroFusion2)** (Dar-Yen Chen and Yi-Zhe Song), the 1–2 step
distillation of Z-Image-Turbo, in three smaller formats that run in **stock ComfyUI**: no custom nodes, the normal
**Load Diffusion Model** node, and ComfyUI's own int8 / W6A8 / W4A8 kernels. They are about **1.7× faster** per step
than bf16 on an RTX 4090 and half to a quarter of its size. All files are made from the publisher's
`nf2-bf16.safetensors` (sha256 `a1e11422…`).

**Use the GPTQ files.** They have the same size, layout and speed as the plain conversions and are closer to bf16 in
every format. For 2 steps, each GPTQ file has a **step-1 file** (the publisher's de-distillation LoRA merged in before
quantizing), which cuts the 2-step error by another 21–33%.

| Format | Size | 1 step, 4090 | Error, 1 step | Error, 2 steps with the LoRA | Error, 2 steps with the step-1 file |
|---|---|---|---|---|---|
| bf16 ([original](https://huggingface.co/ChenDY/NitroFusion2/blob/main/nf2-bf16.safetensors)) | 12.31 GB | 0.50 s | 0 | 0 | – |
| **[int8 GPTQ](diffusion_models/nitrofusion2_int8_convrot_gptq.safetensors)** | 6.18 GB | 0.29 s | 11.3% | 8.7% | **6.9%** |
| **[W6A8 GPTQ](diffusion_models/nitrofusion2_w6a8_gptq.safetensors)** | 5.02 GB | 0.30 s | 13.8% | 12.9% | **8.6%** |
| **[W4A8 GPTQ](diffusion_models/nitrofusion2_w4a8_gptq.safetensors)** | 3.49 GB | 0.29 s | 25.8% | 24.0% | **18.5%** |
| [int8](diffusion_models/nitrofusion2_int8_convrot.safetensors), plain | 6.18 GB | 0.29 s | 13.4% | 9.3% | – |
| [W6A8](diffusion_models/nitrofusion2_w6a8.safetensors), plain | 5.02 GB | 0.30 s | 17.5% | 14.0% | – |
| [W4A8](diffusion_models/nitrofusion2_w4a8.safetensors), plain | 3.49 GB | 0.29 s | 33.6% | 26.0% | – |

Files, in `diffusion_models/`:
- `nitrofusion2_int8_convrot_gptq.safetensors`, `nitrofusion2_w6a8_gptq.safetensors`,
  `nitrofusion2_w4a8_gptq.safetensors`: the GPTQ files, for 1 step and for step 2 of 2
- `nitrofusion2_int8_convrot_gptq_step1.safetensors`, `nitrofusion2_w6a8_gptq_step1.safetensors`,
  `nitrofusion2_w4a8_gptq_step1.safetensors`: their step-1 files (same size each), for step 1 of 2
- `nitrofusion2_int8_convrot.safetensors`, `nitrofusion2_w6a8.safetensors`, `nitrofusion2_w4a8.safetensors`: the
  plain conversions published first

Time is the sampler at 1024×1024 (ComfyUI master `fb2b26fda`, comfy-kitchen 0.2.41), measured on the plain files;
the GPTQ files use the same layout and kernels. **Error** is the relative error of the model's prediction against bf16
for the same input: 12 prompts × 4 noise samples at 1024×1024, the 2-step figures averaged over both steps. A one-step
prediction from pure noise reacts strongly to small weight changes, and nearly all of that error is fine texture: the
pictures keep bf16's composition, faces and text (below). Use the numbers to rank the files against each other, not
to compare with other models.

## Use

1. Put the files in `ComfyUI/models/diffusion_models/`: one GPTQ file for 1 step; the same file and its `_step1` file
   for 2 steps.
2. The text encoder and VAE are Z-Image-Turbo's: [`qwen_3_4b.safetensors`](https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors)
   in `text_encoders/` and [`ae.safetensors`](https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors) in `vae/`.
3. Open a workflow from `example_workflows/` (int8 selected; pick another file in the subgraph's loaders):
   - [1 step](example_workflows/nitrofusion2_1step_gptq.json): the publisher's 1-step workflow.
   - [2 steps with a step-1 file](example_workflows/nitrofusion2_2step_gptq_step1.json): the publisher's 2-step
     workflow with a second **Load Diffusion Model** for step 1 in place of the LoRA. No LoRA file is needed.

Settings as published: euler / simple, CFG 1; 1 step at shift 3; 2 steps at shift 6.

**Why a step-1 file.** The official 2-step workflow applies the de-distillation LoRA at 0.5 on step 1. On a quantized
file ComfyUI re-quantizes the LoRA-patched weights with fresh scales and random rounding, so step 1 loses the
calibration (the plain and GPTQ files end up nearly equal there). The step-1 file has the LoRA merged in before
quantizing and is calibrated on step 1 itself. Both files are loaded during a 2-step run (W4A8: 7.9 GB VRAM peak).
The LoRA route still works with every file: the publisher's
[2-step workflow](example_workflows/nitrofusion2_2step_quantized.json) with
[`nf2-dedistill-lora.safetensors`](https://huggingface.co/ChenDY/NitroFusion2/resolve/main/nf2-dedistill-lora.safetensors)
in `loras/`. The [plain 1-step workflow](example_workflows/nitrofusion2_1step_quantized.json) is there too.

## Pictures

One step with the GPTQ files, seed 42, 1024×1024, the same prompt and noise for every file (top: bf16, int8; bottom:
W6A8, W4A8). The plain files' version of each sheet is in `assets/` (the same name without `_gptq`).

![portrait](assets/compare_1step_portrait_gptq.jpg)
![text](assets/compare_1step_text_gptq.jpg)
![detail](assets/compare_1step_detail_gptq.jpg)
![layout](assets/compare_1step_layout_gptq.jpg)

## How they were made

ComfyUI's own quantization formats (comfy-kitchen):

- **What is quantized:** all 202 linear layers of the 30 main blocks and the 4 refiner blocks (attention qkv and out,
  the three feed-forward layers, adaLN): 6.142B of the model's 6.155B weights. Embedders, norms and the final layer
  stay bf16.
- **int8:** ConvRot (block Hadamard rotation of 256), one scale per row, 8-bit activations.
- **W6A8 / W4A8:** 6-bit / 4-bit weights in the rotated basis with an FP8 scale per group of 16, 8-bit activations.
- **Plain files:** comfy-kitchen's own conversion, no calibration.
- **GPTQ files:** the rotation and rounding in fp32, a search over each group's FP8 scale, then GPTQ in the rotated
  basis (act order, damping 0.01), every weight snapped to the exact value the kernel decodes. Calibration: 48 prompts
  that are not among the evaluation prompts, at about one megapixel, with every model call of both official modes.
- **Step-1 files:** the de-distillation LoRA merged into bf16 at 0.5 with ComfyUI's own patch code (the merged model
  matches bf16 + LoRA exactly), then the same GPTQ on statistics of step 1 alone.

## License and credit

Apache-2.0, as the original: [LICENSE](LICENSE), changes listed in [NOTICE](NOTICE). The model is NitroFusion2 by
Dar-Yen Chen and Yi-Zhe Song, built on [Z-Image-Turbo](https://github.com/Tongyi-MAI/Z-Image) by Tongyi-MAI; the
workflows are the publisher's; the step-1 files contain the publisher's de-distillation LoRA, merged. Paper:
[arXiv 2611.05648](https://arxiv.org/abs/2611.05648).

```bib
@article{chen2026nitrofusion2,
    title={NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers},
    author={Chen, Dar-Yen and Song, Yi-Zhe},
    journal={arXiv preprint arXiv:2611.05648},
    year={2026}
}
```