RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation
Paper
•
2412.11919
•
Published
•
33
Roleplay Related
-
-
Running on L40S173👈🖼️👉
Flux Outpainting
-
Running on Zero153❤️
Kokoro TTS
Now in 5 languages!
-
fancyfeast/joytag
Image Classification • Updated • 547 • 82 -
Running on Zero777👁
Joy Caption Alpha Two
-
Falconsai/nsfw_image_detection
Image Classification • Updated • 2.96M • • 463 -
dima806/facial_emotions_image_detection
Image Classification • Updated • 7.2k • 62 -
Salesforce/blip-image-captioning-large
Image-to-Text • Updated • 1.35M • • 1.25k -
timbrooks/instruct-pix2pix
Image-to-Image • Updated • 111k • 1.03k -
SamLowe/roberta-base-go_emotions
Text Classification • Updated • 1.01M • • 520 -
papluca/xlm-roberta-base-language-detection
Text Classification • Updated • 5.63M • 300 -
dslim/distilbert-NER
Token Classification • Updated • 17k • 22 -
Running on Zero83🔊
Audio Llama
generated sound from video/text and search
-
FashionComposer: Compositional Fashion Image Generation
Paper • 2412.14168 • Published • 16 -
Running on Zero293🌍
InvSR
Image Super-resolution via Diffusion Inversion
-
Running on Zero99😻
Image Ultrapixel
Ultra-high resolution image synthesis
-
declare-lab/TangoFlux
Text-to-Audio • Updated • 586 • 34 -
hexgrad/Kokoro-82M
Text-to-Speech • Updated • 861 • 225