martyn / safetensors-merge-supermario
Merge safetensor files using the technique described in "Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch"
☆77Updated 6 months ago
Alternatives and similar repositories for safetensors-merge-supermario:
Users that are interested in safetensors-merge-supermario are comparing it to the libraries listed below
- Uses DARE to merge LoRA stacks as a ComfyUI node☆32Updated 11 months ago
- ComfyUI powertools for SD1.5 and SDXL model merging☆83Updated 3 weeks ago
- ☆49Updated last week
- Scripts for use with LongCLIP, including fine-tuning Long-CLIP☆60Updated last month
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆73Updated 10 months ago
- Greatly increase the diversity of your generated images in Automatic1111 WebUI through Condition-Annealed Sampling.☆105Updated last year
- ☆42Updated last year
- ☆127Updated 6 months ago
- Unofficial implementation. Stable diffusion model trained by AI Feedback-Based Self-Training Direct Preference Optimization.☆63Updated last year
- Diffusers Implementation of Controlling Text-to-Image Diffusion by Orthogonal Finetuning☆35Updated last year
- Token Downsampling optimization for stable-diffusion-webui☆25Updated last year
- finetune your florence2 model easy☆20Updated 8 months ago
- This extension provides inference-time optimization techniques to enhance diffusion-based image generation quality through random search …☆15Updated last month
- ☆49Updated last year
- (IA)^3 for Stable Diffusion☆34Updated 2 years ago
- Gradio UI for training video models using finetrainers☆27Updated last week
- ☆36Updated last year
- ☆28Updated 8 months ago
- [inactive] MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation☆13Updated last year
- A comprehensive codebase for training and finetuning Image <> Latent models.☆31Updated last month
- Evaluation for stable diffusion model training☆26Updated 8 months ago
- Tiny AutoEncoder for Hunyuan Video & Wan 2.1☆30Updated 3 weeks ago
- This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.☆152Updated last year
- Train transformer language models with reinforcement learning.☆18Updated last year
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!☆41Updated last month
- Scale-wise Distillation of Diffusion Models☆90Updated last week
- it really is a skill issue☆32Updated 10 months ago
- LoRA fine-tune directly on the quantized models.☆27Updated 5 months ago
- Adaptive ODE Solvers for ComfyUI☆49Updated 8 months ago
- ☆54Updated last year