Все модели
Полный список отсортирован по популярности на Replicate.
SDXL fine-tuned on Davinci drawings
Generate synced sounds for any video and return it with its new soundtrack - now enhanced in version 1.5 for improved sound synchronization and realism
Generating Natural Images with Direct Patch Distribution Matching
Upscale videos + images with BSRGAN
Automatic Speech Recognition with Word-level Timestamps & Diarization
Arbitrary-steps Image Super-resolution via Diffusion Inversion
Bach chorale generation and harmonization
Anthropic's most intelligent model with state-of-the-art coding, reasoning, and agentic capabilities
A Flux fine-tune of the Rider-Waite tarot card deck (1909)
Zonos-v0.1 by Zyphra, voice cloning, 5 languages and emotion control
FLUX Dev Model (Text2Img and Img2Img)
Remove image background with custom model to better result.
LoRA, fp16 vintedois-diffusion-v0-1
Create a 3D photo from single in-the-wild 2D images
Zephyr-7B-beta, an LLM trained to act as a helpful assistant.
Audio Reactive Stable Diffusion
🎨AnimateDiff Prompt Travel🧭 Seamlessly Navigate and Animate Between Text-to-Image Prompts for Dynamic Visual Narratives
A flux lora trained on a 1980s cyberpunk aesthetic
High-Resolution Image Synthesis with Latent Diffusion Models
Synthesize drawings to match a text prompt
Segments an audio recording based on who is speaking
SDXL fine-tuned on currencies
Van Gough on Stable Diffusion via Dreambooth
Face Restoration
wizard-mega-13b quantized with AWQ and served with vLLM
Finte-tuned Stable Diffusion on high quality 3D images with a futuristic Sci-Fi theme
Qwen-14B-Chat is a Transformer-based large language model, which is pretrained on a large volume of data, including web texts, books, codes, etc.
A large, stereo MusicGen that acts as a useful tool for music producers
Caricature Generation via StyleGAN Feature Map Modulation
An SDXL fine-tune on Apple Vision Pro
Realistic Vision V5 with OpenPose
DO NOT USE - Broken - Only Public For API Usage & Debugging
Generate subtitles (.srt and .vtt) from audio files using OpenAI's Whisper models.
SegmentAnything Model (SAM) automatic mask generator
The model transforms real-life image to Ghibli Style Art Images.
Use kontext to turn any image into an emoji, using a lora by starsfriday
Zero-shot classifier which classifies text into categories of your choosing. Returns a dictionary of the most likely class and all class likelihoods.
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation
Exploiting Diffusion Prior for Real-World Image Super-Resolution
Ultimate anime-themed finetuned SDXL model and the latest installment of the Animagine XL series
Make realistic images of real people instantly (w/ ip-adapter-plus-face_sdxl_vit-h)
GPU accelerated replay renderer / video data clipper for comma.ai connect's openpilot route data. SEE README.
Tools to train a generative model on arbitrary audio samples
Photorealistic FX by RunDiffusion with LoRA integrated. Works as good or better than RealisticVision.
观照AI
RealVisXL_V3.0, fine-tuned on Apple's emojis
Cartoonifies an image