qwen-image-edit-nvpcb-ovsl2sl Model by NVIDIA

Follow the steps below to download and run the NVIDIA NIM inference microservice for this model on your infrastructure of choice.

Step 1
Get Credentials

Export your personal credentials as environment variables:

Bash

export NGC_API_KEY=<PASTE_API_KEY_HERE>

Step 2
Pull and Run the NIM

Bash

echo "$NGC_API_KEY" | docker login nvcr.io --username '$oauthtoken' --password-stdin

Pull and run the NIM with the command below.

Bash

# Create the cache directory on the host machine.
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p "$LOCAL_NIM_CACHE"
chmod 777 $LOCAL_NIM_CACHE
                        
docker run -it --rm --name=nim-server \
  --runtime=nvidia --gpus='"device=0"' --shm-size=16GB \
  -e NIM_MODEL_VERSION=qwen-image-edit-nvpcb-ovsl2sl \
  -e NGC_API_KEY=$NGC_API_KEY \
  -p 8000:8000 \
  -v "$LOCAL_NIM_CACHE:/opt/nim/.cache/" \
  nvcr.io/nim/qwen/qwen-image-edit:latest

When you run the preceding command, the container downloads the model, initializes a NIM inference pipeline, and performs a pipeline warm up. A pipeline warm up typically requires up to three minutes. The warm up is complete when the container logs show Pipeline warmup: start/done.

Step 3
Test the NIM

Bash

invoke_url="http://localhost:8000/v1/infer"

input_image_path="input.png"
curl https://raw.githubusercontent.com/NVIDIA/physical-ai-data-factory/refs/heads/main/docs/workflows/physical-ai-defect-image-generation/media/paidf-computex26-media/component-0201_LARGE_H040.png > $input_image_path
image_b64=$(base64 -w 0 $input_image_path)

echo '{
    "prompt": "Render this PCB component crop in the style of an NVPCB raked-solder-light photograph: dark reddish board with bright orange-red and blue specular highlights on the solder pads, photorealistic textures.",
    "negative_prompt": " ",
    "image": "data:image/jpeg;base64,'${image_b64}'",
    "steps": 30,
    "cfg_scale": 4.0,
    "seed": 42
}' > payload.json

output_image_path="result.jpg"

response=$(curl -X POST $invoke_url \
    -H "Accept: application/json" \
    -H "Content-Type: application/json" \
    -d @payload.json )
response_body=$(echo "$response" | awk '/{/,EOF-1')
echo $response_body | jq .artifacts[0].base64 | tr -d '"' | base64 --decode > $output_image_path

For more details on getting started with this NIM including configuring using parameters, visit the Visual GenAI NIM docs.

qwen-image-edit-nvpcb-ovsl2sl

Step 1Get Credentials

Step 2Pull and Run the NIM

Step 3Test the NIM

Step 1
Get Credentials

Step 2
Pull and Run the NIM

Step 3
Test the NIM