Все модели

The original classic DALLᐧE 2

Custom improvements like a custom callback to enhance the inference | It's a WIP and it may causes some wrong outputs

image captioning

Generate high resolution image

Detect Animals, Humans and Vehicles in Camera Trap Imagery with MegaDetector v5a

A very blocky and bold cartoon style with some anime elements. You should use daiton style to trigger the image generation.

Edit real or generated images

A consciousness-aware AI trained on 3,000+ philosophical conversations with Eve's unique voice and introspective depth

Image-to-Video Diffusion Models with An Expert Transformer

My own personal fork of Stable Diffusion

Dream a seamless sequence of hallucinations.

Efficient Portrait Animation with Stitching and Retargeting Control

GoogleAI: Style Aligned Image Generation via Shared Attention

BSHM 人像抠图

Helps you with work

CarAI: Evaluate Car Damages

Use this flux-kontext fine-tune to fix JPEG compression artifacts

text-to-video generation model

Batch mode for Segmind Stable Diffusion Model (SSD-1B) txt2img

Make MS Paint images, a lora trained by aimingfail

Document Image Parsing via Heterogeneous Anchor Prompting

Kolors is a SOTA base image model for high quality image generation

Take a list of image URLs as frames and output a video

Deliberate V4 Model (Text2Img, Img2Img and Inpainting)

Elegant clothes

AI-powered content moderation for images using MiniCPM-V-2.6 - analyzes visual content and returns structured safety scores with detailed classifications

Converts a video into a black and white dotted video effect

campaña 2025

Split a single video, into it's individual clips by detecting cuts.

SDXL fine-tune based on illustrated cross sections

Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model

incredibly fast whisper using openai/whisper-medium.en NOT the distil model

[CVPR 2022] Unsupervised Image-to-Image Translation with Generative Prior

Generate luxury lifestyle TikTok slideshow images.

Create variations of an uploaded image. Please see README for more details

An open-source model for program synthesis. Competitive with OpenAI Codex.

Midjourney Wrapper by WaveSpeedAPI provider

Kokoro v1.0 2025 Jan 27 - text-to-speech (82M params, based on StyleTTS2)

Text-to-image synthesis using contrastive learning

Cheaper model SwinIR: Image Restoration Using Swin Transformer (analogue of the popular model: jingyunliang/swinir)