Все модели

LoRA Inference model with Stable Diffusion

Generates speech from text

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

ProteusV0.4: The Style Update - enhances stylistic capabilities, similar to Midjourney's approach, rather than advancing prompt comprehension

The best Pony-SDXL models! Current one is based on Pony Realism.

RESEARCH/NON-COMMERCIAL USE ONLY: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models

Apollo 7B - An Exploration of Video Understanding in Large Multimodal Models

The fastest open source TTS model without sacrificing quality.

CLIP Interrogator (for faster inference)

Faster and cheaper Whisper-AI Large-v2 responses. JAX implementation of OpenAI's Whisper model for up to 15x speed-up (doesn't support TPU).

Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This is the SUPIR-v0Q model and does NOT use LLaVA-13b.

Train subjects or styles faster than ever

Animate Stable Diffusion by interpolating between two prompts

High performance and lightweight object detection models

A state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions

Applies various image effects and transformations to enhance and manipulate images.

Upscale images with the latent diffusion superresolution model

Align text to audio with exact word timings. All characters supported!

4MP text-to-image generation with enhanced cinematic-quality image generation with precise style control, improved text rendering, and commercial design optimization.

An improved outpainting model that supports LoRA urls. This model uses PatchMatch to improve the mask quality.

Portrait Style Transfer with VToonify

An AI system that can create realistic images and art from a description in natural language.

A 13 billion parameter Llama tuned for code completion

ProteusV0.4: The Style Update

Kandinsky 3.0 Model (Text2Img and Img2Img)

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

A simple model to detect and crop face found in image, made for https://outfit.fm

Join the Granite community where you can find numerous recipe workbooks to help you get started with a wide variety of use cases using this model. https://github.com/ibm-granite-community

Inference model for FLUX 1.1 [pro] Ultra using custom `finetune_id`. Supports 4MP images and raw mode for realism

LatentSync: generate high-quality lip sync animations

Bria Increase resolution upscales the resolution of any image. It increases resolution using a dedicated upscaling method that preserves the original image content without regeneration.

Gen-4 Image Turbo is cheaper and 2.5x faster than Gen-4 Image. An image model with references, use up to 3 reference images to create the exact image you need. Capture every angle.

State of the art video generation model. Veo 2 can faithfully follow simple and complex instructions, and convincingly simulates real-world physics as well as a wide range of visual styles.

Models fine-tuned from NoobAI-XL/Illustrious-XL series.

A Step Towards Music Generation Foundation Model text2music

Turn any description into pixel art

2.5 billion parameter image model with improved MMDiT-X architecture

Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets

Personalized Image Animator

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators

Microsoft's tool to convert Office documents, PDFs, images, audio, and more to LLM-ready markdown.

SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

A step-distilled version of flux 2 down to 1s.

Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis

ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement