ljleb/sd-mecha
Executable State Dict Recipes
When creating new AI models, particularly for image generation or language tasks, you often want to combine elements from several existing models to get a unique blend of capabilities. This tool helps you create a 'recipe' for merging different AI models, taking your existing model files (like Stable Diffusion or LLMs) and outputting a single, new model file. It's designed for AI practitioners, researchers, or creatives who fine-tune and customize AI models.
Available on PyPI.
Use this if you need to combine multiple AI models into a new one, especially if you're dealing with very large models or want to perform many merges without running out of memory.
Not ideal if you're looking to train a new AI model from scratch or just want to use existing models without customization.
Stars
81
Forks
10
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Dependencies
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ljleb/sd-mecha"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
SJTU-DENG-Lab/Discrete-Diffusion-Forcing
Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference
declare-lab/tango
A family of diffusion models for text-to-audio generation.
Li-Jinsong/DAEDAL
[ICLR 2026] Official repository of "Beyond Fixed: Training-Free Variable-Length Denoising for...
SalesforceAIResearch/CoDA
Salesforce AI Research's open diffusion language model
ZhanqiuHu/flash-dlm-experimental
Implementation of Flash-DLM (paper: FlashDLM: Accelerating Diffusion Language Models via...