so vits models
1.0.0
Please open and collect information related to AI news and AI new media: https://link3.cc/ainews
Collect various llm, so-vits-svc, stable-diffusion-related models, application, and datasets.
Cooperate with ChatGLM, help you read the papers, and it is complete and accurate: https://www.aminer.cn/
| type | address | Function | Collected quantity | |
|---|---|---|---|---|
| 1 | LLM-Chat | https://github.com/sekift/so-vits-models/blob/main/llm-chat.md | Dialogue Model | 20+ |
| 2 | LLMs | https://github.com/sekift/so-vits-models/blob/main/llm-models.md | Large model | 20+ |
| 3 | so-vits-svc | https://github.com/sekift/so-vits-models/blob/main/so-vits-models.md | sound | 80+ |
| 4 | stable-diffusion | https://github.com/sekift/so-vits-models/blob/main/stable-diffusion-models.md | Pictures, images | 70+ |
| 5 | virtual-digital-person | https://github.com/sekift/so-vits-models/blob/main/virtual-digital-person.md | Virtual digital people/generate videos | 10- |
| 6 | prompt-engineering | https://github.com/sekift/so-vits-models/blob/main/prompt-engineering.md | Prompt Project | 10- |
| 1 | A review of LLM model (must read) Overview of code model | https://github.com/RUCAIBox/LLMSurvey https://arxiv.org/abs/2303.18223 https://arxiv.org/abs/2311.07989 |
|---|---|---|
| 2 | Ng's DL teaching video of technical cooperation with technology small notes on others' Chinese notes Github | https://www.deeplearning.ai/short-courses/ https://github.com/sekift/so-vits-models/blob/main/stude-deeplearning-wu.md https://blog.csdn.net/df007df/category_12457193.html https://github.com/Starcloud-Cloud/java-langchain/tree/master |
| 3 | Visual GPT Reproduction Tutorial Original Github | https://github.com/sekift/so-vits-models/blob/main/visual-chatgpt-build.md https://github.com/microsoft/TaskMatrix |
| 4 | Wisdom, Spark, and Wenxin Review | Click on the link |
| 5 | AI Algorithm Engineer Route | https://www.huaxiaozhuan.com/ |
| 6 | The latest AI paper collection | http://www.paperreading.club/ |
| 7 | AIGC Research Collection | https://gofurther.feishu.cn/docx/Enofdl25BotoVrxth8ec4rNBn5c |
| Serial number | type | Raceway |
|---|---|---|
| 1 | Word | 1.Q&A 2. Chat 3. Continue writing 4. Analysis and summary 5. Programming 6. Translation |
| 2 | image | 1. Literary pictures 2. Pictures and texts 3. Modify 4. Change your face 5.HD 6. Lossless amplification 7. Comic face 8. Art QR code 9. Turn to 3D 10. Turn color 11. Object detection 12. Face recognition 13. Expanded image |
| 3 | voice | 1. Wensheng's pronunciation 2. Phonetics and literacy 3. Tone replacement 4. Generate songs 5. Background music |
| 4 | video | 1. Wensheng Video 2. Pictures and videos 3. Video generation video 4. Video text/picture 5. Object detection 6. Face recognition 7. Virtual Live Streaming |
Exclusive to other fields
1. Logical analysis
2. Mathematical proof/deduction
