Explore

I want to…

Upscale images

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

Restore images

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

Flux fine-tunes

Browse the diverse range of fine-tunes the community has custom-trained on Replicate

Make 3D stuff

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

Latest models

An example of a rudimentary Q&A assistant for ACME SL

Updated 9 runs

ZeST: Zero-Shot Material Transfer from a Single Image

Updated 1.4K runs

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

Updated 41.2K runs

lightweight text-to-speech (TTS) model, trained on 10.5K hours of audio data

Updated 1.4K runs

Mixtral 8x22b v0.1 Zephyr Orpo 141b A35b v0.1

Updated 136 runs

Mixtral-8x22b-v0.1-Instruct-Open-Hermes

Updated 237 runs

Midjourney v6 text-to-image quality model but Open and Decentralized

Updated 4.8K runs

Updated 116 runs

Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Updated 6K runs

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

Updated 363 runs

Updated 73 runs

A large, stereo MusicGen that acts as a useful tool for music producers

Updated 3.4K runs

Mixtral-8x22b-v0.1-4bit

Updated 212 runs

Use a subset of https://github.com/barun-saha/slide-deck-ai to create powerpoint slides from a json description - using python-pptx (https://github.com/scanny/python-pptx)

Updated 235 runs

Generates Images in the Big Medium Style

Updated 939 runs

multilingual text2image latent diffusion model

Updated 10M runs

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

Updated 4K runs

Turn a face into 3D, emoji, pixel art, video game, claymation or toy

Updated 11.7M runs

EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling

Updated 93 runs

Free Lunch towards Style-Preserving in Text-to-Image Generation by InstantX team, with ControlNet

Updated 509 runs

繁花 style 测试

Updated 105 runs

Free Lunch towards Style-Preserving in Text-to-Image Generation by InstantX team

Updated 1.8K runs

Updated 178K runs

MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens

Updated 421 runs

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

Updated 60.6K runs

Open Sora Plan Text To Video

Updated 1.6K runs

Domain Consistent Resolution Adapter for Diffusion Models: generating consistent images with resolutions outside of their trained domain

Updated 1.4K runs

sticker maker fork from fofr

Updated 568 runs

Realistic interior design with text and image inputs

Updated 237K runs

Updated 470 runs

Generate a video transitioning from one image to another using SEINE model

Updated 2.2K runs

Outputs a relevance/similarity score or a list of scores for a pair or pairs of string data. FP16 enabled.

Updated 111 runs

Updated 74 runs

Updated 54.4K runs

Updated 69 runs

LoRA + Iterative 4x Upscale ComfyUI Workflow

Updated 3.1K runs

Updated 895.7K runs

@pharmapsychotic 's CLIP-Interrogator, but 3x faster and more accurate. Specialized on SDXL.

Updated 1.2M runs

An implementation of ByteDance/SDXL-Lightning-8step

Updated 541 runs

Capture a website screenshot

Updated 720.3K runs

Vanitas style paintings

Updated 100 runs

Genetic algorithm like mixing of SDXL models

Updated 522 runs

Audio-Driven Synthesis of Photorealistic Portrait Animations

Updated 8.4K runs

Updated 23 runs

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions

Updated 104 runs

Arc2Face: A Foundation Model of Human Faces

Updated 1.5K runs

GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

Updated 594 runs

DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

Updated 479 runs

Best Human detection and Object Detection Background removal.

Updated 8.7K runs

Tuning-free framework to achieve high appearance and temporal consistency in video editing

Updated 919 runs