Все модели
Полный список отсортирован по популярности на Replicate.
Look! A Dylan!
An enhanced version of sd-interior-design
Text-to-Video Diffusion Models with An Expert Transformer
This is an excellent method for converting blurry facial images into high-definition ones.
a model to get images
EpicRealism with all Controlnet Models included
reverse-engineers images, faithfully reproducing prompts with precision
Stable Diffusion 3 with Differential Diffusion inpainting (experimental)
This model is actually: prompthero / openjourney-v4
CogvideoX Keyframe Interpolation by Zhengcong Fei
make a music
FLUX.1-Dev LoRA Training by Huggingface Diffusers
QVQ-72B-Preview by Qwen is an experimental research model focusing on enhancing visual reasoning capabilities
Distilled version of Whisper
Nvidia Automatic speech-to-text recognition (ASR) in 4 languages (English, German, French, Spanish)
Language Models for Code
The world best model to imagine the limitless world of Arcanea
An 8k context text embedding model served FAST with ONNX on GPU. Check the examples tab to see different ways to run it.
Flux LoRA for creating watercolor styled illustrations. Use 'watercolor illustration in the style of WTRSCPE003' to trigger the model.
Generate character posters from the Red Dead Redemption 2 universe
a
MusicGen trained on NewJeans with vocals
laysv2 outputs with Rococo paintings. Goal is to do like a sci fi flesh gothic.
update the official flux-redux-dev to support lora.
Detects if an image is real or fake.