1 18

Elifarley Callado Coelho Cruz

elifarley

AI & ML interests

None yet

Recent Activity

liked a model 9 days ago

defog/sqlcoder-7b-2

liked a Space 3 months ago

Qwen/Qwen2-Math-Demo

liked a model 3 months ago

THUDM/codegeex4-all-9b

View all activity

Organizations

elifarley's activity

liked a model 9 days ago

defog/sqlcoder-7b-2

Text Generation • Updated Feb 12, 2024 • 133k • 311

liked a Space 3 months ago

260

Qwen Math Demo

🧮

Describe and solve math problems from images or text

liked a model 3 months ago

THUDM/codegeex4-all-9b

Text Generation • Updated Jul 18, 2024 • 568 • 244

liked a Space 3 months ago

1.3k

MagicQuill

🪶

liked a dataset 3 months ago

fka/awesome-chatgpt-prompts

Viewer • Updated Jan 6 • 203 • 10.9k • 7.37k

liked a model 3 months ago

Kortix/FastApply-7B-v1.0

Text Generation • Updated Oct 27, 2024 • 7.96k • 19

reacted to singhsidhukuldeep's post with 🔥 3 months ago

Post

1909

It's not every day you see the No. 1 ranked paper of the day open-sourcing a very powerful image editing app!

Fascinating to see MagicQuill - a groundbreaking interactive image editing system that makes precise photo editing effortless through advanced AI!

The system's architecture features three sophisticated components:

1. Editing Processor:
- Implements a dual-branch architecture integrated into a latent diffusion framework
- Utilizes PiDiNet for edge map extraction and content-aware per-pixel inpainting
- Features a specialized UNet architecture with zero-convolution layers for feature insertion
- Employs denoising score matching for training the control branch
- Processes both structural modifications via scribble guidance and color manipulation through downsampled color blocks
- Maintains pixel-level control through VAE-based latent space operations

2. Painting Assistor:
- Powered by a fine-tuned LLaVA multimodal LLM using Low-Rank Adaptation (LoRA)
- Trained on a custom dataset derived from Densely Captioned Images (DCI)
- Processes user brushstrokes through specialized Q&A tasks for add/subtract/color operations
- Features bounding box coordinate normalization for precise stroke localization
- Implements streamlined single-word/phrase outputs for real-time performance

3. Idea Collector:
- Built as a modular ReactJS component library
- Supports cross-platform deployment via HTTP protocols
- Compatible with Gradio and ComfyUI frameworks
- Features comprehensive layer management and parameter adjustment capabilities
- Implements real-time canvas updates and preview generation

The system outperforms existing solutions like SmartEdit and BrushNet in edge alignment and color fidelity while maintaining seamless integration with popular AI frameworks.

What are your thoughts on AI-powered creative tools?