---
license: apache-2.0
base_model:
- Qwen/Qwen-Image-Edit
pipeline_tag: image-to-image
tags:
- gguf-connector
- gguf-node
widget:
- text: >-
    remove all UI text elements from the image. Keep the feeling that the characters and scene are in water. Also, remove the green UI elements at the bottom
  output:
    url: workflow-demo1.png
- text: >-
    the anime girl with massive fennec ears is wearing cargo pants while sitting on a log in the woods biting into a sandwitch beside a beautiful alpine lake
  output:
    url: workflow-demo2.png
- text: >-
    the anime girl with massive fennec ears is wearing a maid outfit with a long black gold leaf pattern dress and a white apron mouth open holding a fancy black forest cake with candles on top in the kitchen of an old dark Victorian mansion lit by candlelight with a bright window to the foggy forest and very expensive stuff everywhere
  output:
    url: workflow-demo3.png
---
## **qwen-image-edit-gguf**
- use 8-step (lite-lora auto applied); save up to 70% loading time
- run it with `gguf-connector`; simply execute the command below in console/terminal
```
ggc q6
```
>
>GGUF file(s) available. Select which one to use:
>
>1. qwen-image-edit-iq4_nl.gguf
>2. qwen-image-edit-q2_k.gguf
>3. qwen-image-edit-q4_0.gguf
>4. qwen-image-edit-q8_0.gguf
>
>Enter your choice (1 to 4): _
>
- opt a `gguf` file in your current directory to interact with; nothing else

![screenshot](https://raw.githubusercontent.com/calcuis/gguf-pack/master/q6.png)

## **run it with gguf-node via comfyui**
- drag **qwen-image-edit** to > `./ComfyUI/models/diffusion_models`
- *anyone below, drag it to > `./ComfyUI/models/text_encoders`
  - option 1: just **qwen2.5-vl-7b-edit** [[7.95GB](https://huggingface.co/calcuis/pig-encoder/blob/main/qwen_2.5_vl_7b_edit-q2_k.gguf)]
  - option 2: both **qwen2.5-vl-7b** [[4.43GB](https://huggingface.co/chatpig/qwen2.5-vl-7b-it-gguf/blob/main/qwen2.5-vl-7b-it-q4_0.gguf)] and **mmproj-clip** [[608MB](https://huggingface.co/chatpig/qwen2.5-vl-7b-it-gguf/blob/main/mmproj-qwen2.5-vl-7b-it-q4_0.gguf)]
  - option 3: just **qwen2.5-vl-7b-test** [[5.03GB](https://huggingface.co/calcuis/qwen-image-edit-gguf/blob/main/qwen2.5-vl-7b-test-q4_0.gguf)]
- drag **pig** [[254MB](https://huggingface.co/calcuis/pig-vae/blob/main/pig_qwen_image_vae_fp32-f16.gguf)] to > `./ComfyUI/models/vae`

![screenshot](https://raw.githubusercontent.com/calcuis/comfy/master/qi-edit.png)

*note: option 1 (pig quant) is an all-in-one choice; for option 2 (llama.cpp quant), you need to prepare both text-model and mmproj-clip; option 3 (llama.cpp quant) is an experimental attempt, a merge (text+mmproj), similar to option 1, an all-in-one choice also but pig x llama.cpp crossover

<Gallery />

![screenshot](https://raw.githubusercontent.com/calcuis/comfy/master/qi-edit-lite.png)

- get more gguf encoder either [here](https://huggingface.co/calcuis/pig-encoder/tree/main) (pig quant) or [here](https://huggingface.co/chatpig/qwen2.5-vl-7b-it-gguf/tree/main) (llama.cpp quant)

## **run it with diffusers**
- might need the most updated diffusers; for i quant support, should after this [commit](https://github.com/huggingface/diffusers/commit/28106fcac4fd13e7ced5c9eb6803f107e804a08f); install the updated git version diffusers by:
```
pip install git+https://github.com/huggingface/diffusers.git
```

- see example inference below (edit it if needed):
```py
import torch, os
from diffusers import QwenImageTransformer2DModel, GGUFQuantizationConfig, QwenImageEditPipeline
from diffusers.utils import load_image

model_path = "https://huggingface.co/calcuis/qwen-image-edit-gguf/blob/main/qwen-image-edit-iq4_nl.gguf"

transformer = QwenImageTransformer2DModel.from_single_file(
    model_path,
    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
    torch_dtype=torch.bfloat16,
    config="callgg/image-edit-decoder",
    subfolder="transformer"
    )
pipeline = QwenImageEditPipeline.from_pretrained("callgg/image-edit-decoder", transformer=transformer, torch_dtype=torch.bfloat16)
print("pipeline loaded")
pipeline.enable_model_cpu_offload()
image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
prompt = "Add a hat to the cat"
inputs = {
    "image": image,
    "prompt": prompt,
    "generator": torch.manual_seed(0),
    "true_cfg_scale": 2.5,
    "negative_prompt": " ",
    "num_inference_steps": 20,
}
with torch.inference_mode():
    output = pipeline(**inputs)
    output_image = output.images[0]
    output_image.save("output.png")
    print("image saved at", os.path.abspath("output.png"))
```

### **reference**
- base model from [qwen](https://huggingface.co/Qwen)
- diffusers from [huggingface](https://github.com/huggingface/diffusers)
- comfyui from [comfyanonymous](https://github.com/comfyanonymous/ComfyUI)
- gguf-node ([pypi](https://pypi.org/project/gguf-node)|[repo](https://github.com/calcuis/gguf)|[pack](https://github.com/calcuis/gguf/releases))
- gguf-connector ([pypi](https://pypi.org/project/gguf-connector))