AI Models List

Building Detection (Geoscience)

1. Datasets for satellite building segmentation
2. Model for satellite city segmentation
3. Segmenting Buildings in Satellite Images
4. Mask2former swin large mapillary vistas panoptic
5. Maskformer Satellite Trees

Voice Cloning

1. Model for Kanye voice cloning
2. Real Time Voice Cloning
3. https://huggingface.co/anton-l/wav2vec2-xls-r-common_voice-tr-ft-stream

Image Super Resolution

1. Search super-resolution in huggingface
2. magnific
3. Image Resolution Enhancer (IBM)
4. keras-io/super-resolution
5. ldm-super-resolution-4x-openimages

Image clear

1. deblur
2. maxim-tf
3. maxim
4. NAFNet

Speech2Text:

1. Speech to Text
2. Speech to Text 2
3. turboscribe.ai
4. wbbbbb/wav2vec2-large-chinese-zh-cn Important
5. Google speech to text supported languages
6. openai/whisper-large-v3

Digital Human

1. CiroN2022/digital-human
2. Kedreamix/Digital-Human-Weights
3. Efficient 3D Articulated Human Generation with Layered Surface Volumes
4. Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models
5. Creating digital humans: Capture, Modeling, and Synthesis
6. Digital-human on Sourceforge
7. The World of Digital Humans: Where AI Meets Realism
8. awesome-digital-human
9. Digital Human Software for Blender

Image to Video

motexture/VSeq2VSeq
animate anything
stabilityai/stable-video-diffusion-img2vid-xt

Text to Video

hotshotco/Hotshot-XL
cerspense/zeroscope_v2_576w
damo-vilab/text-to-video-ms-1.7b
damo-vilab/modelscope-damo-text-to-video-synthesis
guoyww/animatediff-motion-adapter-v1-5-2
camenduru/potat1
guoyww/animatediff-motion-lora-zoom-in

Text to Speech

1. coqui/XTTS-v2 Support Chinese, voice clone, emotion, etc..
2. speechbrain/tts-tacotron2-ljspeech
3. facebook/fastspeech2-en-ljspeech Only English is supported
4. suno/bark-small More research is needed, not good enough as example on colab
5. microsoft/speecht5_tts Effect is good, need to find models for other languages
   SpeechT5 on Github
6. facebook/mms-tts-engExample efficient is good, need to explore for other language.
7. suno/bark Example on Google Colab

Text to Image

1. dataautogpt3/OpenDalleV1.1 Good
2. stabilityai/stable-diffusion-xl-base-1.0 Better

Sketch

TencentARC/t2i-adapter-sketch-sdxl-1.0 **
TencentARC/t2iadapter_sketch_sd15v2 **

cosc/sketchstyle-cutesexyrobutts

microsoft/beit-base-patch16-224-pt22k-ft22k
Linaqruf/sketch-style-xl-lora