Explore

I want to…

Restore images

Models that improve or restore images by deblurring, colorization, and removing noise

Upscale images

Upscaling models that create high-quality images from low-quality images

Make 3D stuff

Models that generate 3D objects, scenes, radiance fields, textures and multi-views.

Latest models

Updated 108 runs

a model to get images

Updated 148 runs

Recraft v3 (code-named red_panda) is a state-of-the-art text-to-image model from https://recraft.ai, with the ability to generate SVG vector graphics

Updated 938 runs

Recraft v3 (code-named red_panda) is a state-of-the-art text-to-image model from https://recraft.ai

Updated 6.9K runs

Kolors: Effective Training of Diffusion Model for Photorealistic Text-to-Image Synthesis

Updated 4 runs

Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models

Updated 12 runs

Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation

Updated 7 runs

Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping

Updated 6 runs

SDXL-Lightning: Progressive Adversarial Diffusion Distillation

Updated 8 runs

Improved Distribution Matching Distillation for Fast Image Synthesis

Updated 5 runs

Adversarial Diffusion Distillation

Updated 9 runs

Updated 26 runs

Phased Consistency Model

Updated 11 runs

Latent Consistency Models: Synthesizing High-Resolution Images with Few-step Inference

Updated 8 runs

Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis

Updated 7 runs

Baskettball player Darnell Williams

Updated 133 runs

Updated 7 runs

Updated 30 runs

Run any python code

Updated 560 runs

The current model is used for graphics replacement processing

Updated 16 runs

Ostris AI-Toolkit for StableDiffusion3.5-Large LoRA Training

Updated 13 runs

# Interior Decoration Space Scaling - First Use Case

Updated 27 runs

Flux fine tuned on Dojo's ninja mascot. Use "DOJONINJA" in your prompt to trigger the model.

Updated 14 runs

Remodels interior

Updated 38 runs

Updated 57 runs

2.5 billion parameter image model with improved MMDiT-X architecture

Updated 1.5K runs

Updated 183 runs

Updated 64 runs

Updated 46 runs

Updated 30 runs

Updated 76 runs

A flux fine-tune based on neo-impressionism

Updated 327 runs

Images of Yaya, a mature woman

Updated 47 runs

Updated 223 runs

Analyzes music to determine song structure, bpm, downbeats, and demuxes audio

Updated 225 runs

Sayak Paul's cartoonizer, deployed to replicate. Here's the model: https://huggingface.co/instruction-tuning-sd/cartoonizer

Updated 19 runs

Updated 10 runs

Updated 4 runs

flux.1-lite-8B-alpha by Freepik

Updated 77 runs

Updated 7 runs

Updated 8 runs

Updated 19 runs

Updated 6 runs

Creates images in the style of craisee.com. Use it with ... in the style of CRAISEE

Updated 78 runs

Updated 3 runs

Updated 103 runs

Fast FLUX DEV -> Flux Controlnet Canny, Controlnet Depth , Controlnet Line Art, Controlnet Upscaler - You can use just one controlnet or All - LORAs: HyperFlex LoRA , Add Details LoRA , Realism LoRA

Updated 13.2K runs

Fine-tune StableDiffusion3.5-Large with Hugging Face Diffusers

Updated 107 runs

Stable Diffusion 3.5 Large - LoRA Explorer

Updated 330 runs

Updated 9 runs