Pruna-Qwen-Image-2.1 is a set of LoRA adapters that let Qwen/Qwen-Image-2.1 generate and edit images in only 5 or 8 steps. The adapters load on top of the base model, so the pipeline, text encoder, and VAE stay unchanged. Training is based on DMD. Improved using Qwen.

v0.1: first release, work in progress. Pruna-Qwen-Image-2.1 does not yet match the visual quality of the base model. We are still improving the distillation and will update this repository as new versions become available.

Variants

Both adapters are v0.1. Pick one based on whether you need quality or speed.

Each adapter is trained for its own sigma schedule. Load only one at a time.

Prompts, editing, and resolution

The adapters were trained at 1K resolution only, with a mix of simple and upsampled prompts, text-to-image generation, and single- and multi-image editing with up to 3 reference images. Prompt upsampling is optional; detailed prompts usually give better results.

Start at 1024 × 1024 and use at most 3 reference images for editing. Higher resolutions (including 2K) and more reference images may work, but are outside the training coverage, and quality may vary. The 2K timings below show inference speed, not a guarantee of quality at that resolution.

Benchmarking

Use a table; Hugging Face can otherwise render the <img> elements as separate blocks.

Text-to-image with the official Qwen model-card example prompt, BF16, batch size 1, on one NVIDIA H100 80GB. Median of 3 requests after one warmup per configuration. Includes prompt encoding, denoising, and decoding; excludes PNG saving, model loading, and warmup. Base: 40 steps with KV cache on; Pruna-Qwen-Image-2.1: 5 or 8 steps with KV cache off, as configured for this benchmark. The examples below enable KV caching for Pruna-Qwen-Image-2.1; the chart has not been remeasured with that setting. LoRAs were unmerged; no CFG, compilation, or CPU offload. These timings do not imply equal image quality.

Quickstart

Runs text-to-image and image editing with the same pipeline. Needs a CUDA GPU.

pip install 'torch>=2.4.0' 'transformers>=5.17' accelerate peft pillow
pip install git+https://github.com/huggingface/diffusers@6256aa7666cedd47443adc8f82da9a10e110b09c

import torch
from PIL import Image
from diffusers import FlowMatchEulerDiscreteScheduler, QwenImage21Pipeline

STEPS = 8  # 8 for higher quality, 5 for higher speed

# The terminal sigma 0 is appended by the scheduler.
SIGMAS = {
    5: [1.0, 0.94, 6 / 7, 2 / 3, 0.4],
    8: [1.0, 14 / 15, 6 / 7, 10 / 13, 2 / 3, 6 / 11, 0.4, 2 / 9],
}[STEPS]

pipe = QwenImage21Pipeline.from_pretrained(
    "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16
).to("cuda")
pipe.load_lora_weights(
    "PrunaAI/Pruna-Qwen-Image-2.1",
    weight_name=f"p_qwen_image_2.1_{STEPS}step_v0.1.safetensors",
)

# Use the sigmas exactly as given: no extra shifting.
pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_config(
    pipe.scheduler.config,
    use_dynamic_shifting=False,
    shift=1.0,
    shift_terminal=None,
)

For Text-to-Image

Longer, more descriptive prompts give better results.

image = pipe(
    prompt=(
        'A glowing neon shop sign that reads "QWEN IMAGE 2.1", mounted on a brick wall '
        "in a narrow city alley at night. Heavy rain, wet pavement reflecting pink and "
        "blue light, shallow depth of field, cinematic photograph."
    ),
    width=1024,
    height=1024,
    generator=torch.Generator("cuda").manual_seed(42),
    num_inference_steps=STEPS,
    sigmas=SIGMAS,
    true_cfg_scale=1.0,
    use_kv_cache=True,
).images[0]

For Image Editing

image = pipe(
    prompt="Change the background to a sunset beach",
    image=Image.open("input.png").convert("RGB"),
    generator=torch.Generator("cuda").manual_seed(42),
    num_inference_steps=STEPS,
    sigmas=SIGMAS,
    true_cfg_scale=1.0,
    use_kv_cache=True,
).images[0]

Recommended settings

• Use the sigma schedule that matches your adapter, and keep the scheduler at shift=1.0 with dynamic shifting off so the sigmas are not shifted twice.
  • 8-step: 1 → 14/15 → 6/7 → 10/13 → 2/3 → 6/11 → 0.4 → 2/9 → 0 (shift 2, computed as σ = 2t / (1 + t) on evenly spaced t)
  • 5-step: 1 → 0.94 → 6/7 → 2/3 → 0.4 → 0
• No CFG. Keep true_cfg_scale=1.0 and do not pass a negative prompt.
• Keep the LoRA strength at 1.0.
• Write detailed prompts for text-to-image. Longer prompts that describe the subject, setting, lighting, and style work noticeably better than short ones.

Limitations

• This is a first version. Quality is below that of the base model.
• The 5-step adapter is faster than the 8-step one, but its images are visibly worse.
• Short or vague text-to-image prompts give weaker results.
• The adapters are only intended for the settings above. Other step counts, schedules, or CFG values are not supported.

What this is not

• Not a standalone model. It needs the Qwen/Qwen-Image-2.1 base weights.
• Not a replacement for the base model when you need its full quality.
• Not a finished release. Expect the weights to change in future versions.

License

Pruna-Qwen-Image-2.1 is a derivative of Qwen-Image-2.1 and is distributed under the Qwen RESEARCH LICENSE AGREEMENT. Review its use restrictions before using or redistributing the adapters.

Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved.

What's next?

• Use Pruna-Qwen-Image-2.1 to generate and edit images with Qwen-Image-2.1 in a few steps.
• Compress your own models with Pruna and give us a ⭐️ for more efficiency!
• Want to use our optimized image models right away? Check P-Image-Ideogram and P-Image-Edit.

.model-button { display: inline-flex; flex-direction: row; justify-content: center; align-items: center; gap: 8px; padding: 8px 20px; border: none; border-radius: 8px; background: #9334e9; color: #ffffff; font-size: 14px; font-weight: 400; line-height: 1; text-decoration: none; white-space: nowrap; cursor: pointer; box-sizing: border-box; overflow: visible; opacity: 1; }

Try our models