Find what you need for your workflow.

Korean Kws2

This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on the None dataset. It achieves the following results on the evaluation set: Loss: 0.2259 Accuracy: 1.0

SDXL Lightning LoRAs

model.safetensors

model.safetensors

Unirec 0.1b

[Paper] [Code] [ModelScope Demo] [Hugging Face Demo] [Local Demo] \[UniRec40M Dataset\]

LTX 2.3 DEV GGUF (unsloth)

Tatyana_Ali_PMv1a_ZImage.safetensors

amafluxAmateurRealistic_21FP16.safetensors

Kaiko (Original Character) - Anima/Illustrious/PonyXL

Kaiko Goch, an anthropomorphic guira cuckoo, an original character created by Kukuhich/kykywka999 ( ). LoRA was train on (mostly) her artwork with her permission.

Videomae Base Finetuned Ucf101 Subset

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.5436 Accuracy: 0.8286

Tks 10ru Style

Works best at 0.75 weight.

GLM OCR BF16

This model was converted to MLX format from zai-org/GLM-OCR using mlx-vlm version 0.3.11. Refer to the original model card for more details on the model.

Ukr Council Extractor Qwen2.5 1.5b

A QLoRA adapter that extracts five header/signature fields from the text of a Ukrainian local-council decision (рішення) and returns them as strict JSON. It is a distillation target: a frontier teacher (Claude Opus,...

model.safetensors

SenseNova U1 8B MoT

🚀 SenseNova U1 is a new series of native multimodal models that unifies multimodal understanding, reasoning, and generation within a monolithic architecture. It marks a fundamental paradigm shift in multimodal AI:...

persephoneFluxNSFWSFW_20FP8.safetensors

Oberon

Flux2-Klein-9b-PuffyNipples-v2.safetensors

Animij

kwFemale KREA2

Suggested 8 steps and cfg 1 for generation with this Lora.