Все модели

sdxl-lcm finetuned for Kids Colouring Pages

PixArt Sigma 900M is a text-to-image generation model based on the PixArt Sigma architecture

Controlling Vision-Language Models for Universal Image Restoration

Direct Preference Optimization (DPO) is a method to align diffusion models to text human preferences by directly optimizing on human comparison data

A flux dev lora fine-tuned on bad 2004 digital photography

Generate a new image from an input image with RPG V4

herge_style on Stable Diffusion via Dreambooth

Fusing Diffusion Paths for Controlled Image Generation

Apple's monocular depth estimation foundation model (Depth Pro)

Realistic text-to-image by TiwazM

Change the background on an image and relight the scene.

The Picsart Text2Video-Zero model leverages the power of existing text-to-image synthesis methods (e.g., Stable Diffusion), making them suitable for the video domain

MagicAnimate using an OpenPose input video

First version of my panorama LoRA (use 1024x512)

Transcribe audios using OpenAI's Whisper with stabilizing timestamps by stable-ts python package.

Pushing the Limits of Mathematical Reasoning in Open Language Models - Base model

An SDXL fine-tune based on studio Ghibli picture stills

This LoRA was created using snapshots of Midwest Furfest 2023, I call it Multiverse Furfest 202X. Trigger word is MFF, adding "fursuit" and "convention" to your prompts seems to help.

Meta's DINOv3 (ViT-L/16 Distilled). A state-of-the-art self-supervised vision transformer trained on the LVD-1689M dataset. Optimized for visual similarity, image retrieval, and dense feature extraction.

FLUX Kontext fine-tune that let's you restyle any image as a PS1 or PS2 video game

SDXL fine-tuned on both Barbie and Tron Legacy

Teach Machines to Paint

Minimal and Universal Control for Diffusion Transformer - demo for Subject-driven generation

✨Stable Diffusion 3 w/ ⚡InstantX's Canny, Pose, and Tile ControlNets🖼️

A refined version of my original MK1 model, with a better focus on fighters with human faces, and different materials (water, ice, fire, etc.)

Transform your image or QR code like never before

SDXL tuned on instagram.com/syhmen paintings

RealVisXL_V3.0, img-to-emoji

OmniGen2: a powerful and efficient unified multimodal model

Styled text-to-drawing synthesis method.

A flux fine tune of my subconscious

Relight – Soft, curtain-filtered relighting that repaints the scene with golden-hour or moody tones using the Relight LoRA.

Consistent Diffusion Features for Consistent Video Editing

SDXL Model (Text2Img, Img2Img and Inpainting)

stable-diffusion-textual-inversion fine-tuned with ugly sonic

Llama2 7B with embedding output

Video to OpenPose

clip interrogator with controlnet sdxl for canny and controlnet v1.1 for the others

Diffusion Models as Text Painters