Все модели

PixArt-Alpha 1024px is a transformer-based text-to-image diffusion system trained on text embeddings from T5

Consistent Self-Attention for Long-Range Image and Video Generation

Simple tool to quickly trim a video or audio file

Image generation model from Reve

Removes Background From Image

Generate a new image given any input text with epiCRealism

multilingual-e5-small: A multi-language text embedding model

Generate videos with specific camera movements

Generate native long-form video, with controllability

Generate subtitles from an audio file, using OpenAI's Whisper model.

Deforum Stable Diffusion

sound separation with demucs

Detailed, higher-resolution images from Stable Diffusion

Visualize the encoded latents of an image

Create a professional headshot photo from any single image

Fast, efficient image variation model for rapid iteration and experimentation.

Nous Hermes 2 - SOLAR 10.7B is the flagship Nous Research model on the SOLAR 10.7B base model..

Fast, high quality text-to-video and image-to-video (Also known as Dream Machine)

Image editing model from Reve

Tryout SegmentAnything Model (SAM) by Meta.

cerate music with open source

A 7 billion parameter Llama tuned for coding and conversation

DeepFake AI

4 step distilled version of FLUX.2 [klein]. A foundation model for maximum flexibility and control

Background removal model developed by BRIA.AI, trained on a carefully selected dataset and is available as an open-source model for non-commercial use.

Realistic Vision V6.0 B1 Model (Text2Img, Img2Img and Inpainting)

Realistic Vision V4.0

Create videos from illustrated input images

Generate a video from an audio clip and a reference image

Mistral-7B-v0.1 fine tuned for chat with the OpenOrca dataset.

AudioSR: Versatile Audio Super-resolution at Scale

stable-diffusion with negative prompts, more scheduler

Generates subtitles from audio using whisperX (faster-whisper-large-v3)

From Sketch to Reality: Transforming Outlines into Lifelike Images

Generate images using a variety of techniques - Powered by Discoart

Object removal, video completion and video outpainting

A fine-tuned SDXL based on GTA V art

Newest balance-striking reranker model from BAAI. Outputs rank scores for query-doc pairs. FP16 inference enabled.

Modify images with a prompt while preserving their structure

Modify images using human pose

auto1111_ds8

Create illusions with img2img and masking support

A 13 billion parameter Llama tuned for coding and conversation

Lyria 2 is a music generation model that produces 48kHz stereo audio through text-based prompts

Ostris AI-Toolkit for Flux LoRA Training (DEPRECATED. Please use: ostris/flux-dev-lora-trainer)