crisostomi/cycle-consistent-model-merging
Codebase for "C2M3: Cycle-Consistent Multi-Model Merging".
This project helps machine learning researchers combine the knowledge from several trained AI models into a single, more powerful model. You provide a set of already-trained models, and it outputs a new, merged model that incorporates their individual strengths. This is for researchers or practitioners working with multiple neural networks who want to consolidate them without retraining.
No commits in the last 6 months.
Use this if you have multiple trained neural network models and want to create a single, more robust model by intelligently merging their parameters.
Not ideal if you need to train new models from scratch or fine-tune existing models on new datasets, as this project focuses on merging already-trained models.
Stars
12
Forks
5
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/crisostomi/cycle-consistent-model-merging"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
bghira/SimpleTuner
A general fine-tuning kit geared toward image/video/audio diffusion models.
mcmonkeyprojects/SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an...
nateraw/stable-diffusion-videos
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
TheDesignFounder/DreamLayer
Benchmark diffusion models faster. Automate evals, seeds, and metrics for reproducible results.