2025-09-20 16:29:07 +00:00
2025-09-18 18:36:01 +00:00
2025-09-20 16:29:07 +00:00
2025-09-18 18:36:01 +00:00
2025-09-18 18:36:01 +00:00
2025-09-18 18:36:01 +00:00

Lucy Edit - ComfyUI

Lucy Edit Dev Logo

🧪 GitHub  |  🤗 Huggingface  |  📖 Playground  |  📑 Technical Report  |  💬 Discord


image

Put the woman in gothic black jeans and leather jacket and crop top under it.

1.2) Put her in a clown outfit.

1.3) Put the woman in a red bikini with an open thick coat above it.

Lucy Edit is a video editing model that performs instruction-guided edits on videos using free-text prompts — it supports a variety of edits, such as clothing & accessory changes, character changes, object insertions, and scene replacements while preserving the motion and composition perfectly.

  • 🏃‍♂️ Motion Preservation - preserves the motion and composition of videos perfectly, allowing precise edits.
  • 🎯 Edit reliability — edits are more robust when compared to common inference time methods.
  • 🧢 Wardrobe & accessories — change outfits, add glasses/earrings/hats/etc.
  • 🧌 Character Changes — replace characters with monsters, animals and known characters. (e.g., "Replace the person with a polar bear")
  • 🗺️ Scenery swap — move the scene (e.g., "transform the scene into a 2D cartoon,")
  • 📝 Pure text instructions — no finetuning, no masks required for common edits

🛠️ Quickstart

Installation

  1. Clone this repo into custom_nodes folder.
  2. Install dependencies: pip install -r requirements.txt

Download Model Weights

  1. Download the appropriate weights for your setup:

  2. Place the weights under: models/diffusion_models/

Usage

Please refer to the "Prompting Guidelines & Supported Edits" section for the best experience.

Lucy Edit Pro (API)

  1. Load the workflow from examples/basic-api-lucy-edit.json.
  2. Get an api key from: https://platform.decart.ai/.

Lucy Edit Dev (Local)

  1. Load the workflow from examples/basic-lucy-edit-dev.json

🎬 Demos

### Sample 1

1.1) Replace the man with an alien wearing the same leather jacket.

1.2) Replace the man witha polar bear.

1.3) Make it snow.

Sample 2


2.1) Replace the woman with Harley Quinn with full make up and a shirt with "Daddy's Lil Monster" written on it.

2.2) Replace the girl with a lego character.

2.3) Change the shit to a Manchester United jersey.

Note: The prompts above are not enriched, the model will react better to enriched prompts - as described in the prompt guideline section below.


🧭 Roadmap

  • ✅ API based custom nodes.
  • ✅ local inference custom nodes.
  • Add support for Lucy Edit Dev/Image API

🔥 Latest News

  • [2025-09-17]: Initial Lucy Edit Dev weights & reference code released.
  • [2025-09-16]: Diffusers integration PR Merged. PR #12340.
  • [2025-09-16]: Diffusers integration PR opened. PR #12340.

Prompting Guidelines & Supported Edits

Lucy Edit is built for precise, realistic, and identity-preserving video edits.
Prompts with ~20–30 descriptive words work best. Using the right trigger words helps the model understand your intent.

Trigger Words

  • Change → Clothing or color modifications
  • Add → Adding animals or objects
  • Replace → Object substitution or subject swap
  • Transform to → Global scene or style transformations

Supported Edit Types

1. Clothing Changes

✅ Best performance. Lucy Edit excels at swapping outfits while preserving motion, pose, and identity.
Example: “Change the shirt to a kimono with wide sleeves and patterned fabric.”

2. Human/Character Replacement

✅ Strong results. Works well for transforming people into new characters or creatures. Detailed prompts are key.
Example: “Replace the person with a tiger, striped orange fur, muscular build, and glowing green eyes.”
Example: “Replace the person with an 2D anime character, big eyes, blue gown and battle scars.”

3. Replace Objects

✅ Reliable for structure-preserving swaps. Ideal when replacing one object with another of similar scale.
Example: “Replace the apple with a glowing crystal ball emitting blue light.”

4. Color Changes

⚠️ Mixed reliability. Sometimes subtle, sometimes exaggerated. Works best with precise descriptions.
Example: “Change the jacket color to deep red leather with a glossy finish.”

5. Add Objects

⚠️ Often attaches to the subject. Works best for wearable or handheld props.
Example: “Add a golden crown on the person’s head, decorated with ornate jewels.”

6. Global Transformations

⚠️ Effective for backgrounds or scene-wide changes, might alter the subject Alter environment or style, might, Often changes the identity of the subject. Example: “Transform the sunny beach into a snowy tundra with falling snowflakes.”

Additional Notes

  • Strengths: Lucy Edit excels at identity conservation, edit precision, realism, and prompt adherence.
  • Detail matters: Longer prompts (20–30 words) describing style, appearance, and context improve results.
  • Frame count: 81-frame generations produce better temporal consistency than shorter clips.

📬 Contact

S
Description
No description provided
Readme MIT
11 MiB
Languages
Python 100%