README
Awesome AIGC
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.
Text
This category takes text as input.
Text to Text
| 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] |
Text to Image
| 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] |
Text to Video
Text to Mesh
| 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] |
Text to Voice
Text to Music
Image
This category takes single image or multiple images as input.
Image to Text
Image to Image
Image to Mesh
Image to Video
| Name | TRL | More Links |
|---|---|---|
| Make-A-Video | 4-5 | [Paper] |
Enhancement
This category contains enhancement methods to other AIGCs.
| Name | TRL | More Links |
|---|---|---|
| ControlNet | 5-6 | [Paper] |
| GPTCache | 5-6 | [Code] |
Contributing
Contributions are super welcome. When you do it, please follow the contribution guidelines.
Contributors
4 commits
Similar repos
README
Awesome AIGC
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.
Text
This category takes text as input.
Text to Text
| 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] |
Text to Image
| 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] |
Text to Video
Text to Mesh
| 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] |
Text to Voice
Text to Music
Image
This category takes single image or multiple images as input.
Image to Text
Image to Image
Image to Mesh
Image to Video
| Name | TRL | More Links |
|---|---|---|
| Make-A-Video | 4-5 | [Paper] |
Enhancement
This category contains enhancement methods to other AIGCs.
| Name | TRL | More Links |
|---|---|---|
| ControlNet | 5-6 | [Paper] |
| GPTCache | 5-6 | [Code] |
Contributing
Contributions are super welcome. When you do it, please follow the contribution guidelines.
Similar repos
Contributors
4 commits