martyn / safetensors-merge-supermarioLinks
Merge safetensor files using the technique described in "Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch"
☆81Updated last year
Alternatives and similar repositories for safetensors-merge-supermario
Users that are interested in safetensors-merge-supermario are comparing it to the libraries listed below
Sorting:
- ☆129Updated 2 months ago
- Scripts for use with LongCLIP, including fine-tuning Long-CLIP☆63Updated 9 months ago
- finetune your florence2 model easy☆21Updated last year
- Diffusers Implementation of Controlling Text-to-Image Diffusion by Orthogonal Finetuning☆35Updated 2 years ago
- Greatly increase the diversity of your generated images in Automatic1111 WebUI through Condition-Annealed Sampling.☆108Updated last year
- ComfyUI powertools for SD1.5 and SDXL model merging☆94Updated 8 months ago
- Unofficial implementation. Stable diffusion model trained by AI Feedback-Based Self-Training Direct Preference Optimization.☆65Updated last year
- ☆43Updated last year
- ☆54Updated 2 years ago
- Model code for inferencing T5☆66Updated 9 months ago
- ☆37Updated last year
- Set of Utilities I Have Coded to Help Me Train RPGv6 on Flux1☆83Updated last year
- ☆126Updated 9 months ago
- (IA)^3 for Stable Diffusion☆35Updated 2 years ago
- This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.☆158Updated 2 years ago
- Token Downsampling optimization for stable-diffusion-webui☆26Updated last year
- Gradio UI for training video models using finetrainers☆33Updated 7 months ago
- This extension provides inference-time optimization techniques to enhance diffusion-based image generation quality through random search …☆23Updated 9 months ago
- ☆50Updated last year
- SliderSpace: Decomposing the Visual Capabilities of Diffusion Models☆111Updated 2 weeks ago
- Uses DARE to merge LoRA stacks as a ComfyUI node☆36Updated last year
- ☆32Updated last year
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!☆48Updated 6 months ago
- [inactive] MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation☆13Updated last year
- Useful utilities for huggingface☆21Updated 2 months ago
- Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models☆50Updated 2 years ago
- A comprehensive codebase for training and finetuning Image <> Latent models.☆48Updated 9 months ago
- ☆120Updated 2 years ago
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆82Updated last year
- Testbed for the fastest SD pipelines☆35Updated 2 years ago