xiaomomy/MAMBO-G

MAMBO-G: A training-free, magnitude-aware adaptive guidance framework for accelerating Classifier-Free Guidance (CFG). Dynamically mitigates early-step overshoot in flow-matching models (SD3.5, Qwen-Image, Wan2.1) to achieve 3x-4x speedup with high visual fidelity. Integrated into Hugging Face Diffusers.

25
/ 100
Experimental
No Package No Dependents
Maintenance 13 / 25
Adoption 3 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

4

Forks

—

Language

Python

License

—

Category

stable-diffusion-implementations

Last pushed

Mar 08, 2026

Commits (30d)

0

GitHub
Stable Diffusion Implementations · 64 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/xiaomomy/MAMBO-G"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

Acly/krita-ai-diffusion

Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional...

67

sayakpaul/dreambooth-keras

Implementation of DreamBooth in KerasCV and TensorFlow.

42

deep-diver/LoRA-deployment

LoRA fine-tuned Stable Diffusion Deployment

39

charrywhite/LanPaint-diffusers

LanPaint diffusers version code

33

aws-samples/amazon-sagemaker-personalized-generative-ai

This project simplifies personalized Gen-AI SaaS apps. We fine-tune pre-trained models for...

32

Explore Generative AI Tools

All categories Trending Generative AI directory Insights