Find what you need for your workflow.

ControlNetrunwayml/stable-diffusion-v1-5

ControlNet Segment Interior

These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below.

ControlNetstabilityai/stable-diffusion-xl-base-1.0

Sam2 Tiny Tracking

The SAM2 tiny checkpoint used in the Model Garden Cell and Bacterium Tracking demo: class-agnostic video segment-and-track where pretrained detectors have no labels, e.g. a neutrophil chasing a bacterium.

Starlight Prod

Task: Steganography detection (and method / bit-order heads) Architecture: BalancedStarlightDetector (multi-stream CNN + fusion gate) Input streams: pixel, meta, alpha, LSB, palette, format/content features (see GGUF...

Satnogs Signal Classifier

ResNet-18 fine-tuned to classify SatNOGS waterfall spectrograms as signal vs no-signal (narrowband FSK/GFSK cubesat telemetry). A read-only triage aid — it suggests, it does not auto-vet.

Ddpm Celebahq Finetuned Butterflies 2epochs

pipeline = DDPMPipeline.frompretrained('Skeen04/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image

InstantMesh

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

ControlNet Openpose SDXL 1.0

These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with OpenPose (v2) conditioning. You can find some example images in the following.

CheckpointIllustriousv3.0

ModelCivitai

sweetHoney 甜蜂蜜スイートハニー illus

v3 additional sample images below in model gallery- as always : ) again used civitai popular prompts for testing and gallery. So far I am happy with results, it shows it is more creative and still following the...

VerifiedB

Otherfacebook/hubert-base-ls960

Helix v0.7

Helix is a neural spatial audio model that converts mono audio to First-Order Ambisonic (FOA) 4-channel format using text-based spatial positioning.

Hubert Finetuned Emotion Audio Dataset

This model is a fine-tuned version of facebook/hubert-base-ls960 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.5474 Accuracy: 0.8289

Otherstable-diffusion-xl-1.0-inpainting-0.1

IDM VTON

This is an official implementation of paper 'Improving Diffusion Models for Authentic Virtual Try-on in the Wild' paper project page

Text modeltiiuae/Falcon-OCR

Falcon OCR FP8

Falcon OCR is a 300M parameter early-fusion vision-language model for document OCR. Given an image, it can produce plain text, LaTeX for formulas, or HTML for tables, depending on the requested output format.

Othergoogle/gemma-4-E4B-it

Gemma 4 E4B It Q8 0 GGUF

This model was converted to GGUF format from google/gemma-4-E4B-it using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Otherfacebook/wav2vec2-xls-r-300m

Xlsr 300m Mizonal3 E3 Lus v2026.06

> Disclaimer / Notice: Details for these are in Peer Review and publications of the paper will be made available soon for more details.

Othergoogle/gemma-4-E4B-it

Sulphur 2 Base

An uncensored video generation model based on LTX 2.3 supporting both t2v and i2v natively, as well as all of the other ltx 2.3 formats.

Gemma 4 E4B It Q4 K M GGUF

This model was converted to GGUF format from google/gemma-4-E4B-it using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Text modelnaver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B

Bigvox HyperCLOVAX Audio

Bigvox은 한국어 음성 인식에 특화된 고성능, 저지연 음성 언어 멀티모달 모델입니다. naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B 기반으로 구축되었습니다. 🚀 End-to-End 음성 멀티모달 구조를 채택하여 음성 입력부터 텍스트 출력까지 하나의 파이프라인에서 처리하며, 추가적인 중간 모델 없이 자연스럽게 멀티모달 처리를 지원합니다.

ControlNetrunwayml/stable-diffusion-v1-5

ControlNet Canny SDXL 1.0

These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with canny conditioning. You can find some example images in the following.