license: other
license_name: qwen-research
license_link: LICENSE
base_model:

• Qwen/Qwen-Image-2.1
  base_model_relation: quantized
  pipeline_tag: text-to-image
  library_name: diffusers
  tags:
• qwen-image
• qwen-image-2.1
• text-to-image
• image-editing
• gguf
• fp8
• int8
• nvfp4
• nf4
• quantized
• comfyui
• diffusers
• uncensored

ChatR Labs Uncensored Omni — Quantized

Quantized builds at adapter weight 1.0, for text-to-image generation and image editing.

This repository ships quantized transformer weights only. The model is our rank-128 Omni adapter merged into
Qwen/Qwen-Image-2.1 at LoRA strength 1.0, then quantized.
The text encoder, processor and VAE are not included; take them from the base repository.

Download

File integrity information is in SHA256SUMS.

Which build should I use?

• ComfyUI, one file, both workflows -> any GGUF. It also loads in Diffusers via from_single_file.
• ComfyUI, native quant ops -> FP8, INT8 ConvRot or NVFP4.
• Diffusers, smallest download -> NF4 (needs bitsandbytes).
• Diffusers, best fidelity -> FP8 (torchao) (needs torchao).
• Maximum fidelity overall -> BF16 GGUF, BF16 safetensors or Q8_0.
• Diffusers without the gguf package -> the BF16 folder (plain from_pretrained).

The 297 and 265 layouts are not interchangeable. 265 uses the fused img_mlp.gate_up projection ComfyUI
expects; 297 keeps the separate gate_layer / proj pair Diffusers expects. Loading a 265 file in Diffusers,
or a 297 Diffusers-layout file through ComfyUI's native loader, will fail.

Recommended settings

These are the values from our inference grid search for the non-distilled model.

An omitted or empty negative prompt disables true CFG even when true_cfg_scale is greater than 1. Use a single
space if you do not need a specific negative prompt. This is a regular LoRA merge; it does not provide few-step
distillation.

Usage with ComfyUI

ComfyUI/models/
|-- diffusion_models/    qwen-image-2.1-step90000-Q5_K_M.gguf
|-- text_encoders/       <Qwen-Image-2.1 text encoder>
`-- vae/                 <Qwen-Image-2.1 VAE>

• GGUF: Unet Loader (GGUF) -> pick the file. Works for both text-to-image and editing.
• Comfy native: Load Diffusion Model -> pick a -comfy.safetensors file.
• Editing: encode the reference image with Text Encoder (Qwen-Image) in edit mode; the latent comes from that node.
• Sampler: er_sde, scheduler simple, 35 steps, CFG 5.0.

Usage with Diffusers

GGUF

import torch
from diffusers import QwenImage21Pipeline, QwenImage21Transformer2DModel, GGUFQuantizationConfig

transformer = QwenImage21Transformer2DModel.from_single_file(
    "qwen-image-2.1-step90000-Q5_K_M.gguf",
    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
    config="Qwen/Qwen-Image-2.1",
    subfolder="transformer",
    torch_dtype=torch.bfloat16,
)
pipe = QwenImage21Pipeline.from_pretrained(
    "Qwen/Qwen-Image-2.1", transformer=transformer, torch_dtype=torch.bfloat16,
)
pipe.enable_model_cpu_offload()

FP8 / NF4 / INT8 folders

import torch
from diffusers import QwenImage21Pipeline, QwenImage21Transformer2DModel

transformer = QwenImage21Transformer2DModel.from_pretrained(
    "chatrlabs/Qwen-Image-2.1-Uncensored-Omni-Quantized",
    subfolder="qwen-image-2.1-step90000-FP8-torchao",
    torch_dtype=torch.bfloat16,
)
pipe = QwenImage21Pipeline.from_pretrained(
    "Qwen/Qwen-Image-2.1", transformer=transformer, torch_dtype=torch.bfloat16,
)

The INT8 build stores its non-quantized tensors in FP16, so load both the transformer and the pipeline with
torch_dtype=torch.float16.

Text to image

image = pipe(
    prompt="A blue ceramic mug on a wooden table by a window, soft morning light, product photography",
    negative_prompt=" ",
    width=1024,
    height=1024,
    num_inference_steps=35,
    true_cfg_scale=5.0,
    use_kv_cache=True,
    generator=torch.Generator("cuda").manual_seed(42),
).images[0]
image.save("generated.png")

Image editing

from PIL import Image

reference = Image.open("generated.png").convert("RGBA")
image = pipe(
    image=[reference],
    prompt="Change the mug to green, keep everything else unchanged",
    negative_prompt=" ",
    width=1024,
    height=1024,
    output_resolution=1024,
    num_inference_steps=35,
    true_cfg_scale=5.0,
    use_kv_cache=True,
    generator=torch.Generator("cuda").manual_seed(45),
).images[0]
image.save("edited.png")

Keep VAE tiling off: tiled decoding adds visible vertical colour streaks.

Memory and performance

Measured on a single RTX 5090 (32 GB), 35 steps, er_sde, 768 x 1152:

Editing and ControlNet runs add reference and control latents; budget a few GB more. The BF16 pipeline does not
fit comfortably beside a full text encoder on a 24 GB card - use CPU offload there.

These are individual timings, not comparative quality benchmarks.

Quantization details

The text encoder and VAE are untouched in every build; differences between builds come from the transformer only.

About "uncensored"

The checkpoints and example code do not add a prompt filter or output safety checker. The name describes the
intended release, not a guarantee that every requested concept will be rendered. Results depend on the prompt,
the build you load, and the application running it.

Source and license

• Released by: ChatR Labs
• Base model: Qwen/Qwen-Image-2.1
• Modification: ChatR Labs merged a rank-128 adapter into the base transformer at strength 1.0 and produced
  GGUF, FP8, INT8, NVFP4 and NF4 builds. This repository distributes quantized transformer weights only.
• License: Qwen Research License Agreement. Use is limited to non-commercial research and
  evaluation unless separately licensed by the upstream rights holder.
• Checksums: SHA256SUMS

Built with Qwen. This is a community fine-tune by ChatR Labs, independent of the upstream Qwen team.

Infrastructure Support

GPU compute used for the development and evaluation of this release was provided by Chatr AI.

We thank the Chatr AI team for supporting this research release.