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 Dev is an open-weight 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.
🚀 First open-source instruction-guided video editing model
🧩 Built on Wan2.2 5B architecture — inherits high-compression VAE + DiT stack, making adapting existing scripts and workflows easy.
🏃♂️ 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.
Please refer to the "Prompting Guidelines & Supported Edits" section for the best experience.
python
1from typing import List
23import torch
4from PIL import Image
56from diffusers import AutoencoderKLWan, LucyEditPipeline
7from diffusers.utils import export_to_video, load_video
8910# Arguments11url ="https://d2drjpuinn46lb.cloudfront.net/painter_original_edit.mp4"12prompt ="Change the apron and blouse to a classic clown costume: satin polka-dot jumpsuit in bright primary colors, ruffled white collar, oversized pom-pom buttons, white gloves, oversized red shoes, red foam nose; soft window light from left, eye-level medium shot, natural folds and fabric highlights."13negative_prompt =""14num_frames =8115height =48016width =8321718# Load video19defconvert_video(video: List[Image.Image])-> List[Image.Image]:20 video = load_video(url)[:num_frames]21 video =[video[i].resize((width, height))for i inrange(num_frames)]22return video
2324video = load_video(url, convert_method=convert_video)2526# Load model27model_id ="decart-ai/Lucy-Edit-Dev"28vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)29pipe = LucyEditPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)30pipe.to("cuda")3132# Generate video33output = pipe(34 prompt=prompt,35 video=video,36 negative_prompt=negative_prompt,37 height=480,38 width=832,39 num_frames=81,40 guidance_scale=5.041).frames[0]4243# Export video44export_to_video(output,"output.mp4", fps=24)
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.
