Find what you need for your workflow.

ZwZ 8B GGUF

These are quantizations of the model ZwZ-8B, using a imatrix created from text\en\medium

epiCRealism XL

chandra-nalaar

Originally posted to HuggingFace by sd-concepts-library Magic: The Gathering Stable Diffusion Textual Inversion Embeddings Check all MTG related models here ! chandra-nalaar on Stable Diffusion This is the concept...

model.safetensors

Virtual Goddess: Leona

This is an embedding of a woman that I've generated consistent faces of thru SD and decided to make into an embedding for easier access in the future. It uses a mere 5 tokens.

IlluRealXL (v0.2)

Surrealism Fantasy Style - KUNGE

This is my first LoRa release, using 248 carefully selected images, iterating 6000 times, and taking 7 hours to train. It boasts amazing detail and generalization; it works very well. Feel free to use your...

Ddpm Celebahq Finetuned

Finetuned using a single epoch.

SDXL Natural Skintone (FP32 VAE)

dggyafslnccZIB.safetensors

makinaFlux_v10.safetensors

LucidDreamer Z

八重咲羽 Sakihane Huya Stellive.safetensors

Whisper Medium Full Clinical R16

This model is a fine-tuned version of openai/whisper-medium on the afrispeech-200 dataset. It achieves the following results on the evaluation set: Loss: 0.7557 Wer: 22.4040 Cer: 8.9223

Ddpm Celebahq Finetuned Butterflies 2epochs

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

model.safetensors

70s Photography Krea2

Lora with a vintage 1970s photography style.

Unet Kvasir Seg

Standard U-Net with: Encoder: 4 levels (64, 128, 256, 512 channels), each with two Conv3x3+BN+ReLU blocks followed by MaxPool2x2 Bottleneck: 1024 channels at 16x16 spatial resolution Decoder: 4 levels mirroring the...

MiniMax H3 Simple workflow | 16GB VRAM 32GB RAM quite fast — v1 — v4

Added ollama prompt helper, tuned optimization/quality.