Все модели

Music-1.5: Full-length songs (up to 4 mins) with natural vocals & rich instrumentation

A powerful vision-language model in the Qwen series

A powerful native multimodal model for image generation (PrunaAI squeezed)

Wan 2.5 image-to-video, optimized for speed

Upscale Portrait Images with ControlNet Tile

SAM 2: Segment Anything v2 (for Images)

Qwen Image 2512 is an improved version of Qwen Image with more realistic human generation, finer textures, and stronger text rendering

Unlimited XL Model (Text2Img, Img2Img and Inpainting)

Bria Background Generation allows for efficient swapping of backgrounds in images via text prompts or reference image, delivering realistic and polished results. Trained exclusively on licensed data for safe and risk-free commercial use

One shot portrait maker.

🖼️✨Background images + prompts to auto-magically relights your images (+normal maps🗺️)

Demo for AnimeGanv2 Face Portrait

This is an optimised version of the hidream-l1-dev model using the pruna ai optimisation toolkit!

Image-to-video at 720p and 480p with Wan 2.2 A14B

Generate 5s 480p videos. Wan is an advanced and powerful visual generation model developed by Tongyi Lab of Alibaba Group

Super fast clothing (and face) segmentation and masking with erosion and dilation capability, made for https://outfit.fm

Sentence embedding using mpnet

Omni-Zero Couples: A diffusion pipeline for zero-shot stylized couples portrait creation.

WAI-NSFW-illustrious-SDXL v.90

Grok 4 is xAI’s most advanced reasoning model. Excels at logical thinking and in-depth analysis. Ideal for insightful discussions and complex problem-solving.

InstantID : Zero-shot Identity-Preserving Generation in Seconds. Using Juggernaut-XL v8 as the base model to encourage photorealism

WhisperX model for spanish language.

A lower-latency image-to-video version of Hailuo 2.3 that preserves core motion quality, visual consistency, and stylization performance while enabling faster iteration cycles.

(Research & Non-commercial use only) Text-Video-to-Audio Synthesis: Generate realistic audio from video and text descriptions

Generate images with Kandinsky 2.2 - Mix text and images

Implementation of SDXL RealVisXL_V1.0

Generate 5s and 9s 720p videos, faster and cheaper than Ray 2

Unsupervised Night Image Enhancement

Flux lora, use "BSstyle004" to trigger image generation

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

(Academic and Non-commercial use only) Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization

Edit images with human instructions

Wan 2.5 text-to-video, optimized for speed

Canny, soft edge, depth, lineart, segmentation, pose, etc

Generate image from text by guiding a denoising diffusion model. Inference is somewhat slow.

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

Fix Diffrent Sizes for each clip. Fork of lucataco/cog-video-merge.git

Hunyuan-Video LoRA Explorer + Trainer

Clone voices to use with Minimax's speech-02-hd and speech-02-turbo

Text-to-audio generation with latent diffusion models

Change or Replace Video Background with any Image

SDXL Image Blending

Flux lora, use "in the style of TOK" to trigger generation, creates half photo half illustrated elements

Text-to-Image Diffusion Models are Zero-Shot Video Generators