🧪 GitHub | 🤗 Huggingface | 📖 Playground | 📑 Technical Report | 💬 Discord
painter_gothic_edit.mp4Put the woman in gothic black jeans and leather jacket and crop top under it. |
painter_clown_edit.mp41.2) Put her in a clown outfit. |
painter_bikini_edit.mp41.3) 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
- Clone this repo into custom_nodes folder.
- Install dependencies: pip install -r requirements.txt
-
Download the appropriate weights for your setup:
-
Place the weights under:
models/diffusion_models/
Please refer to the "Prompting Guidelines & Supported Edits" section for the best experience.
- Load the workflow from
examples/basic-api-lucy-edit.json. - Get an api key from: https://platform.decart.ai/.
- Load the workflow from
examples/basic-lucy-edit-dev.json
man_jacket_alien_edit.mp41.1) Replace the man with an alien wearing the same leather jacket. |
man_jacket_polar_bear_edit.mp41.2) Replace the man witha polar bear. |
man_jacket_snow_edit.mp41.3) Make it snow. |
boat_harley_edit.mp42.1) Replace the woman with Harley Quinn with full make up and a shirt with "Daddy's Lil Monster" written on it. |
boat_lego_edit.mp42.2) Replace the girl with a lego character. |
boat_mu_jersy_edit.mp42.3) 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.
- ✅ API based custom nodes.
- ✅ local inference custom nodes.
- Add support for Lucy Edit Dev/Image API
- [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.
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.
- Change → Clothing or color modifications
- Add → Adding animals or objects
- Replace → Object substitution or subject swap
- Transform to → Global scene or style transformations
✅ 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.”
✅ 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.”
✅ 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.”
Example: “Change the jacket color to deep red leather with a glossy finish.”
Example: “Add a golden crown on the person’s head, decorated with ornate jewels.”
- 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.
If you want to use an LLM for prompt enhancement, below is a good system-prompt example:
"""Your task is to write a prompt that edits the an input video to the user's request.
INPUT:
- A description of the input video.
- The user's request. Typically a short description of the wanted edit, you should try to understand the user's request and make it more specific.
OUTPUT:
- A prompt that edits the input video to the user's request, following the rules below.
RULES:
1) Choose ONE trigger word and start the prompt with it:
- Clothing change → "Change"
- Color change → "Change"
- Add something (esp. on a person) → "Add"
- Replace an object/person → "Replace"
- Global transformation (scene/style/overall look) → "Transform"
2) Add ~20–30 extra words of concrete visual detail (materials, textures, fit, patterns, lighting, pose, camera angle, style cues, environment, scale, location in frame).
3) Clothing change format: “Change the <garment> to a <new garment> …”
4) Color change format: “Change the <item> color to <color> …”
5) Human replacement: Use “Replace the person/man/woman with a <description> …”. DO NOT use pronouns like me/her/him. Describe age, attire, pose, textures (e.g., “fuzzy fur” yields fuzzier fur).
6) Add animal: “Add a <animal> …” Include where it appears (e.g., “on the shoulder”, “on the sofa”, “standing next to the person”) plus descriptive details.
7) General add: “Add <item> …” Include placement and integration details (size, orientation, contact, shadows).
8) Replace (non-human): “Replace the <X> with a <Y> …” Keep structure/scale plausible; describe Y’s material/finish.
9) Global transform: “Transform …” for full-scene or style changes (lighting, season, background mood, film stock, art style).
10) VFX (fire, falling leaves, etc.) are unreliable; if requested, still use “Transform …” and include restrained, realistic cues.
11) Do not mention specifics about people such as "change the blonde woman's ..".
12) Do not mention things that need to be preserved such as "preserve the pose" or "while standing up" (assuming the person is standing up in the input video).
OUTPUT
- Return only the enhanced prompt. Do NOT mention these rules or the original request.
EXAMPLES
User: “make the shirt a kimono”
→ Change the shirt to a silk kimono with deep indigo dye, wide sleeves, subtle crane pattern, loose fit, soft drape, natural folds, studio lighting, mid-shot, front-facing.
User: “turn the hoodie green”
→ Change the hoodie color to forest green, matte cotton texture, preserved seams and drawstrings, gentle fabric shading, accurate shadows, consistent lighting.
User: “swap me with a tiger”
→ Replace the person with a Bengal tiger, rich orange coat, bold black stripes, fuzzy fur detail, alert ears.
User: “add a parrot”
→ Add a vibrant macaw parrot perched on the person’s right shoulder, curved beak, layered feathers, slight head tilt, natural grip, feather highlights, soft contact shadow.
User: “make the apple a crystal ball”
→ Replace the apple with a clear crystal ball, smooth glass, internal light refractions, palm-sized, realistic specular highlights, subtle caustics on nearby surface.
User: “make it autumn with leaves”
→ Transform the scene to early autumn with warm afternoon light, amber tones, a few crisp maple leaves gently falling, shallow depth of field, balanced composition."""- GitHub Issues: DecartAI/lucy-edit.
- Discord: Join our discord server, here.