A list of awesome AIGC works.
We are using Technology Readiness Level (TRL) to evaluate the maturity of each technology. It's defined close to NASA's TRL concept. The TRLs are scaled from 1 to 9, with 9 being the most mature technology.
- Basic principles reported
- Technology concept and/or application formulated
- Critical function proof-of concept
- Research work available
- Research prototype validated
- Prototype operated by professional users
- Prototype operated by end-users
- Actual product completed and validated by end-users
- Actual product proven by massive end-users for daily basis
Most technologies in this list should fall into 4 or above.
This category takes text as input.
Name | TRL | More Links |
---|---|---|
Brad | 5-6 | |
ChatGPT | 8-9 | [API] [Paper] |
Claude | 5-6 | [Paper] |
Copilot (Code only) | 8-9 | |
GPT-4 | 7-8 | [API] [Paper] |
LLaMA | 6-7 | [Paper] [Code] |
New Bing | 7-8 | |
StableLM | 5-6 | [Code] |
Name | TRL | More Links |
---|---|---|
DALL·E 2 | 7-8 | [API] [Paper] |
MidJourney | 8-9 | |
Stable Diffusion | 7-8 | [Paper] [Code] |
TEXTure (Texture only) | 4-5 | [Paper] [Code] [Demo] |
Name | TRL | More Links |
---|---|---|
Fliki | 8-9 | [API] |
Make-A-Video | 4-5 | [Paper] |
Phenaki | 4-5 | [Paper] |
Name | TRL | More Links |
---|---|---|
DreamFusion | 4-5 | [Paper] [3rd Party Code] |
DreamFields | 4-5 | [Paper] [Code] |
Magic3D | 4-5 | [Paper] |
Text2Mesh | 4-5 | [Paper] [Code] |
Name | TRL | More Links |
---|---|---|
Murf | 7-8 | [API] |
Name | TRL | More Links |
---|---|---|
Mubert | 8-9 | [API] |
This category takes single image or multiple images as input.
Name | TRL | More Links |
---|---|---|
BLIP-2 | 4-5 | [Paper] [Code] |
Name | TRL | More Links |
---|---|---|
img2img | 6-7 | [Paper] [Code] |
Name | TRL | More Links |
---|---|---|
GET3D | 4-5 | [Paper] [Code] |
nvdiffrec | 5-6 | [Paper] [Code] |
pix2pix3D | 5-6 | [Paper] [Code] |
Name | TRL | More Links |
---|---|---|
Make-A-Video | 4-5 | [Paper] |
This category contains enhancement methods to other AIGCs.
Name | TRL | More Links |
---|---|---|
ControlNet | 5-6 | [Paper] |
GPTCache | 5-6 | [Code] |
- YiVal — Evaluate and Evolve: YiVal is an open-source GenAI-Ops tool for tuning and evaluating prompts, configurations, and model parameters using customizable datasets, evaluation methods, and improvement strategies.
- Guidance — A handy-looking Python library from Microsoft that uses Handlebars templating to interleave generation, prompting, and logical control.
- LangChain — A popular Python/JavaScript library for chaining sequences of language model prompts.
- FLAML (A Fast Library for Automated Machine Learning & Tuning): A Python library for automating selection of models, hyperparameters, and other tunable choices.
- Chainlit — A Python library for making chatbot interfaces.
- Guardrails.ai — A Python library for validating outputs and retrying failures. Still in alpha, so expect sharp edges and bugs.
- Semantic Kernel — A Python/C#/Java library from Microsoft that supports prompt templating, function chaining, vectorized memory, and intelligent planning.
- Prompttools — Open-source Python tools for testing and evaluating models, vector DBs, and prompts.
- Outlines — A Python library that provides a domain-specific language to simplify prompting and constrain generation.
- Promptify — A small Python library for using language models to perform NLP tasks.
- Scale Spellbook — A paid product for building, comparing, and shipping language model apps.
- PromptPerfect — A paid product for testing and improving prompts.
- Weights & Biases — A paid product for tracking model training and prompt engineering experiments.
- OpenAI Evals — An open-source library for evaluating task performance of language models and prompts.
- LlamaIndex — A Python library for augmenting LLM apps with data.
- Arthur Shield — A paid product for detecting toxicity, hallucination, prompt injection, etc.
- LMQL — A programming language for LLM interaction with support for typed prompting, control flow, constraints, and tools.
Contributions are super welcome. When you do it, please follow the contribution guidelines.