InsightSolver:

• Colab notebooks for exploring and solving operational issues using deep learning, machine learning, and related topics.

Welcome to my Cool Repo! 🤓

This repository contains a lot of notebooks that can be run in Google Colab to understand how to use models immersed in the areas of deep learning, machine learning, and others related to them.

It focuses on applying machine learning, analysis, and data science to identify and automatically solve operational issues in diverse areas.

The vast majority of notebooks are designed to run on the Colab free tier.

Notebook Name	Colab Link	Tasks
Wonder 3D: Single Image to 3D using Cross-Domain Diffusion		image-to-3D stable-diffusion
Latent Consistency Models: Synthesizing High-Resolution Images with Few-step Inference		text-to-image image-to-image video-to-video stable-diffusion
SadTalker: A realistic and stylized talking head video generation method from a single image and audio		image-to-video video-generation
WizardCoder-Python-34B on Colab's free tier - GGUF		text-generation GGUF GGML WizardCoder
SeamlessM4T: Multimodal model for speech translation		translation speech-to-speech speech-to-text text-to-speech
Alternatives to Stable Diffusion "WebUI" on Google Colab's Free Tier		text-to-image stable-diffusion
SDXL 1.0 with T2I Adapter, ControlNet, Inpainting and train LoRA		text-to-image stable-diffusion LoRA inpainting
llama-cpp-python with Llama 2 13B-chat		text-generation GGML Llama 2
AutoGPTQ with WizardCoder 15B		text-generation GPTQ WizardCoder
SDXL 0.9		text-to-image stable-diffusion
Massively Multilingual Speech (MMS)		speech-to-text text-to-speech spoken-language-identification
Segmentation Demos, Metaseg, SegGPT, Prismer		image-segmentation video-segmentation
ControlNet		text-to-image inpainting outpainting stable-diffusion
Track Anything Colab		video-segmentation video-inpainting stable-diffusion
Subtitles transcription and translation		speech-to-text translation
LoRA Stable Diffusion with diffusers		LoRA stable-diffusion text-to-image
DreamBooth Stable Diffusion		DreamBooth text-to-image stable-diffusion
Real ESRGAN and GFPGAN		image-restoration super-resolution
Latent Upscaler		image-restoration super-resolution
CodeFormer: Video Image Restoration		image-restoration video-restoration
VToonify		style-transfer
Inverse Cross Attention SD		text-to-image stable-diffusion inpainting
CrossAttention SD Koiboi		text-to-image stable-diffusion
MAXIM		image_denoising low_light_enhancement image_retouching dehazing_indoors dehazing_outdoors image_deraining image_deblurring
N2V for Image Denoising of Single-Channel Images		image_denoising
OCR with Pytesseract and OpenCV		OCR
Donut		OCR document-parsing
InstructPix2Pix with Diffusers		text-to-image stable-diffusion
Deforum		stable-diffusion text-to-video interpolation
In-painting, Image-to-Image, Depth-to-Image, SD Diffusers		text-to-image stable-diffusion
Stable Diffusion Custom Model		text-to-image stable-diffusion
TPU Stable Diffusion Fast Jax		text-to-image stable-diffusion
AltDiffusion M9 Multilingual CLIP		text-to-image stable-diffusion
Fine-tuned VAE Decoder Compare Stable Diffusion		text-to-image stable-diffusion
Petals: Guanaco-65B, LLaMA-65B, BLOOM and BLOOMZ in Colab		text-generation
Infinity Colab		inpainting outpainting text-to-image stable-diffusion
Music Video Killed The Radio Star, Defusion		text-to-video stable-diffusion
Interpreting Stable Diffusion Using Cross Attention, DAAM, Diffusers		text-to-image stable-diffusion
Deepfloyd IF Free Tier Google Colab		text-to-image stable-diffusion
Segment Anything		image-segmentation
Microsoft Bringing Old Photo Back to Life		image-restoration
UniColoror: A Unified Framework for Multi-Modal Colorization with Transformer		image-restoration
DISCO: Disentangled Image Colorization via Global Anchors		image-restoration
DeOldify Colab		image-restoration
DeOldify VideoColorizer Colab		video-restoration
Deep Exemplar-based Video Colorization		video-restoration
BLOOM BigScience with bitsandbytes int8		text-generation
OPT Open Pre-trained Transformers		text-generation
LLaMA 4-bit Quantization		text-generation GPTQ
ChatPDF h2ogpt		text-generation
Diarization Whisper and Pyannote Transcripts with Speaker Names		speech-to-text diarization
NER Biomedical with Stanza and Summarization		text-generation
Wav2Vec2 Transcription		speech-to-text
Fix Grammar, Punctuation Correction, Language Detection		text-generation
FILM: Video Generation		interpolation
PyTTI Tools and FiLM		interpolation
SAHI and Detectron2		object-detection
SAHI Inference for YOLOv5		object-detection
DE-DETR, Panoptic, and Others		object-detection image-segmentation
Detectron2 Tutorial		object-detection segmentation
Detic_clip and Detectron2		object-detection segmentation
U-2-Net Demonstration Colab 2		background-removal
U-2-Net Step by Step Demonstration		background-removal
DIS Ichotomous Image Segmentation		background-removal

License

Although the code can be Apache 2 or MIT, the models or weights may have commercial restrictions. This repository is intended for educational purposes, and you are encouraged to use the code and notebooks to learn and explore about this topics.

Questions and Discussions

If you have any questions about the licensing, usage, or anything else related to this repository, feel free to open a discussion or raise an issue.