Image Segmentation
Transformers
Safetensors
background-removal
image-matting
BiRefNet
transparency
camouflage
text-preservation
illustration
rgba
custom_code
Instructions to use egeorcun/lucida with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use egeorcun/lucida with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="egeorcun/lucida", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForImageSegmentation model = AutoModelForImageSegmentation.from_pretrained("egeorcun/lucida", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Model card: link the lucida-design space
Verified signature6cbedc9 -
Model card: document lucida-m35-comfy and the design pipeline
Verified signature21b9a5d -
Add lucida-m35-comfy: experimental design-expert weights, folded for ComfyUI
Verified signature138df17
-
Revert model card to v7 + changelog note
Verified signature6ee1112 -
Revert weights to v7 (v13 regressed on real-world layered artwork)
Verified signature6a9abc4
-
Update weights to v13 (soup of the v9 and v13 checkpoints)
Verified signature9165c2e -
Update model card for v13
Verified signature88162ed
-
v7: print-design/sticker category (fixes #2) — design 2x better than all measured rivals; overall now leads every model tested
Verified signature28632b8 -
v7 numbers
Verified signature4013af1
-
v6: edge-crop + mixed-opacity training (fixes #1 — solid parts of transparent objects, frame-cropped subjects)
Verified signaturea34eeda -
v6 benchmark numbers
Verified signature83aef00
-
Upload README.md with huggingface_hub
Verified signaturefcdb138 -
Upload config.json with huggingface_hub
Verified signature10674ff -
Upload README.md with huggingface_hub
Verified signature3e402b6 -
Upload folder using huggingface_hub
Verified signature0c1a283 -
initial commit
Verified signature76383ae