Все модели

Remix the music into another styles with MusicGen Chord

A fashion model

[Quality Mode] Scaling Diffusion Models for High Resolution Textured 3D Assets Generation

TOK trained on 1960 coloring books.

The predecessor to DALLE-2, GLIDE (filtered) with faster PRK/PLMS sampling.

Meta's Llama 2 13b Chat - GPTQ

Generates oil painting images

Delivers high visual fidelity with fast turnaround. Great for daily content creation, marketing teams, and iterative creative workflows.

Apply the style of an image to your image. Upscaling with Clarity is recommended. Twitter/X: @philz1337x

Kolors with style transfer, composition transfer and other IPAdapter techniques

Vectorized dot grid - by Brett from Designjoy

Generate expressive, natural speech with Resemble AI's Chatterbox.

Lip Read silent videos with AI

Generate cartoonish images to be used as game backgrounds.

Inference Airoboros L2 70B 2.1 - GPTQ using ExLlama.

Whisper is a general-purpose speech recognition model.

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

Removes specified objects from image

Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models.

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

Qwen-Image optimized by Pruna AI. Generates high fidelity 1.5MP images in 1s.

Granite-speech-3.3-8b is a compact and efficient speech-language model, specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST).

Image Manipulatinon with Diffusion Autoencoders

Ollama Llama 3.3 70B

Sprite sheets made easy. Give it a whirl!

Nebul.Redmond - Stable Diffusion SD XL Finetuned Model

A 4-megapixel model built on Flux-Schnell and optimized with Pruna for fast, highly detailed image generation.

A Cog implementation of BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation [Face Parsing] (https://github.com/yakhyo/face-parsing).

视频合并

A unified foundation model for prompt-based segmentation in images and videos

Fork of https://replicate.com/zsxkib/ic-light that allows any image resolution

This is a faster VACE-14B model, optimised with pruna, contact us for more at pruna.ai

OpenAI's first o-series reasoning model

Create pencil sketches of anything

Create professional architecture and interior designs

Gemma2 2b Instruction-tuned variant by Google

ThinkDiffusionXL is a go-to model capable of amazing photorealism that's also versatile enough to generate high-quality images across a variety of styles and subjects without needing to be a prompting genius

Artistic Radiance Fields - Transfer the style of an image to a 3D scene (NeRF)

Merge multiple images into clean horizontal or vertical strips with precise alignment and sizing controls.

✍️Step1X-Edit by stepfun-ai, Edit an image using text prompt📸

Generating Conditional 3D Implicit Functions

Generate thumbnails for Youtube using popular templates and styles

Image Mixer Stable Diffusion

A film-grade digital human model that generates realistic video from a single image, audio clip, and optional text prompt.

🎤The best open-source speech-to-text model as of Jul 2025, transcribing audio with record 5.63% WER and enabling AI tasks like summarization directly from speech✨

Cinematic.Redmond has a high capacity to generate Cinematic, artistic images, cars, people, and a wide variety of themes

Take photos in analog film style

Fine-tune MusicGen small, medium and melody models. Also stereo models available.