Все модели
Полный список отсортирован по популярности на Replicate.
Skin – Natural beauty retouch that enhances pores and tonal variation (no plastic skin) via the Skin LoRA.
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
Low-Light Image Enhancement
A fine-tuned SDXL lora based on Tron Legacy
Google's Gemma2 27b instruct model
Use this kontext fine-tune to turn any photo into an old and damaged photo
Bria GenFill enables high-quality object addition or visual transformation. Trained exclusively on licensed data for safe and risk-free commercial use.
Segments an audio recording based on who is speaking (on A100)
Dia 1.6B by Nari Labs, Generates realistic dialogue audio from text, including non-verbal cues and voice cloning
Hunyuan3D-2mv is finetuned from Hunyuan3D-2 to support multiview controlled shape generation.
Real-Time Open-Vocabulary Object Detection
OmniGen: Unified Image Generation
Defog's SQLCoder is a state-of-the-art LLM for converting natural language questions to SQL queries. SQLCoder is a 15B parameter fine-tuned on a base StarCoder model.
Creative Upscale focuses on enhancing details and refining complex elements in the image. It doesn’t just increase resolution but adds depth by improving textures, fine details, and facial features.
CogVLM is a powerful open-source visual language model (VLM)
pix2pix model for predicting pbr texture maps from an albedo texture
InterpAny-Clearer: Clearer anytime frame interpolation & Manipulated interpolation
InstantID : Zero-shot Identity-Preserving Generation in Seconds. Using Dreamshaper-XL as the base model to encourage artistic generations
NeuralBeagle14-7B is (probably) the best 7B model you can find!
Made public only for API calls. Use min-dalle instead-- it's superior.
Regression of musical arousal and valence values
Un-distilled version of FLUX.2 [klein]. Optimized for fine-tuning, customization, and post-training workflows
an open-source, 2B-parameter model built for real-world applications
Deliberate V6 Model (Text2Img, Img2Img and Inpainting)
Nous Hermes 2 - Yi-34B is a state of the art Yi Fine-tune, fine tuned on GPT-4 generated synthetic data
bare pixray for API use
epic xkcd comics
Transfer learning models for music classification by genres, moods, and instrumentation
(Research only) Moondream1 is a vision language model that performs on par with models twice its size
Add colours to old video footage.
Turn an image into a set of images from different 3D angles
A speech-to-text model that uses GPT-4o mini to transcribe audio
datasets: Flickr8k
Image to Image enhancer using DemoFusion
SOTA Open source model trained on licensed data, transforming intent into structured control for precise, high-quality AI image generation in enterprise and agentic workflows.
Open diffusion model for high-quality video generation
Generate 5s and 9s 540p videos
BetterUp Stable Diffusion XL Image Model
Zero-Shot Speech Editing and Text-to-Speech in the Wild
Inference model for FLUX.1 [pro] using custom `finetune_id`
Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling
Use Huggingface model name to test a ANY XL model