camenduru/ml-mgie 🔢📝🖼️ → ❓

▶️ 6.9K runs 📅 Feb 2024 ⚙️ Cog 0.9.4 🔗 GitHub 📄 Paper ⚖️ License

image-editing large-language-model multimodal text-guided-editing

About

Guiding Instruction-based Image Editing via Multimodal Large Language Models

Example Output

Prompt:

"make the frame red"

Output

{"path":"https://replicate.delivery/pbxt/LkDA2ecYabWSdSnQjomeAewvXaPjB5jZMFXIsOZnffshAVpSC/image.png","text":"If the frame of the glasses in the image were made red, the overall appearance of the scene would change significantly.The red frame would draw more attention to the glass and create a stronger contrast with the black frame."}

Performance Metrics

12.28s Prediction Time

87.24s Total Time

All Input Parameters

{
  "seed": 13331,
  "prompt": "make the frame red",
  "text_cfg": 7.5,
  "image_cfg": 1.5,
  "input_image": "https://replicate.delivery/pbxt/KNSKXP6DiykiZn7bEsZoZiaxGmE5o90BSUbDr67KrbOZcAvc/_input_0.jpg"
}

Input Parameters

seed Type: integerDefault: 13331
prompt Type: stringDefault: make the frame red
text_cfg Type: numberDefault: 7.5
image_cfg Type: numberDefault: 1.5
input_image (required) Type: string: Input Image

Output Schema

path Type: stringFormat: uri: Path
text Type: string: Text

Example Execution Logs

/usr/local/lib/python3.10/site-packages/transformers/generation/utils.py:1211: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use a generation configuration file (see https://huggingface.co/docs/transformers/main_classes/text_generation)
warnings.warn(

Version Details

Version ID: cd6688b06dcdcf8b6c614abe400d37d40d85b9e07e438396582a1721686667b7
Version Created: February 10, 2024

Run on Replicate →