Все модели
Полный список отсортирован по популярности на Replicate.
AnimeGANv3: To produce your own animation.
Grad-CAM visualizations for Align before Fuse
dreambooth trained on a very diverse dataset ranging from photographs to paintings
ZavyChromaXL v7, a high contrast and colorful SDXL fine-tune
A collection of anime stable diffusion models with VAEs and LORAs.
A Flux fine-tune of https://replicate.com/zeke the real-life human. Use "ZIKI" in the prompt to activate the trained style.
Generate synced sounds for any video, and return it with its new sound track
Phi-2 by Microsoft
Human pose manipulation for fashion
simple pdf to text from a url using tesseract
Flux dev fine-tuned on alphabet book pages
Very fast img2img for a collaboration with AI in real time
Flux lora, use "CLR" to trigger image generation
Flux lora, use the term "MNALSA" to trigger generation
Input a video. Ask anything about it
Disco Diffusion style on Stable Diffusion via Dreambooth
Upscale images with Stable Diffusion
A LoRA fine-tuned model for generating cute anime-style images.
Add Text & Music to Videos
An SDXL model trained on Marissa Montgomery's oil and gouache paintings
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
A watercolor Aquarell style lora for flux
Convert speech in audio to text w/ `tiny`, `small`, `base`, and `large-v3` models
Editable image generation with MasaCtrl-SDXL
🎧 Kimi-Audio-7B-Instruct, ASR, audio reasoning, captioning, emotion sensing, and TTS into one universal model 🔊
Efficient Diffusion Model for Image Super-resolution by Residual Shifting
Improving the Stability of Diffusion Models for Content Consistent Super-Resolution
Implementation of SDXL RealVisXL_V1.0 img2img
SDXL with prompt weighting available using Compel's syntax. Check the Github link for the docs.
DiT-based video generation model for generating high-quality videos in real-time
Multi-Controlnet + consistency-decoder + INPAINTING + realestic-vision-v5 + Prompt-Weight + Single-Controlnet
Make images in Studio Ghibli art style
ProteusV0.5 is the latest full release built as a sophisticated enhancement over OpenDalleV1.1
Generate music in stereo, restricted to chord sequences and tempo
Replicate port of https://huggingface.co/Envvi/Inkpunk-Diffusion. Finetuned Stable Diffusion model trained on dreambooth. Vaguely inspired by Gorillaz, FLCL, and Yoji Shinkawa.
Upstage/Llama-2-70B-instruct-v2 - GPTQ
Semantic Room Wireframe
A Fast and Stable GAN for Small and High Resolution Imagesets
POC to run inference on Realvisxl2 LoRAs
A small model alternative to o1
A quantized 33B parameter language model from Deepseek for SOTA repository level code completion
AuraSR: GAN-based Super-Resolution for real-world
Emotional conditioned music generation using transformer-based model.
VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing in the Wild