Все модели

Image Paint Style

A ControlNet model designed to enhance the temporal consistency of generated outputs

create interior designers moodboards

Hunyuan fine-tuned on clips from the ponponpon video, use PONPONPON as keyword

llama-2-7b fine-tuned on the samsum dataset for dialogue summarization

Base version of Mamba 1.4B, a 1.4 billion parameter state space language model

A model Flux.1-dev-Controlnet-Upscaler by www.androcoders.in

controlnet version of z-image-turbo with lora support

Rethinking the Role of UNet Encoder in Diffusion Models

Cog implementation of LTX image to video from its diffusers pipeline

任意のフレーズからジャパニーズヒップホップ風の歌詞を生成します

Generates images of a black cat called Ronja

Wan-Alpha text-to-video generation with alpha channel, optimized for Replicate deployment. WebM/WebP output with transparency support.

flan-t5-xl trained on the Memory Alpha Star Trek Wiki

Converts any logo image to pure white while preserving transparency. Perfect for mockups, printing, or overlaying on dark backgrounds. Accepts PNG or JPG input and returns a whitened version of the logo in seconds.

Make a video of anything in Studio Ghibli style

Mobius: Redefining State-of-the-Art in Debiased Diffusion Models

RESIDENTIAL HOUSE

Fine-tune of music gen with tracks from my record label Dream In Audio.

AdcSR: ultra-fast super-resolution, optimized to run faster

HunyuanVideo finetune of an AI avatar from Heygen

Glitchy glitch glitch

Social Media Comment Analysis

A simple Hebrew Diacritizer

Model trained to make PURR artwork

DeepLabV3+ model for high-accuracy binary image segmentation, trained to detect roofs (foreground vs background) and output a grayscale mask.