Model Add-ons
Find adapters that declare compatibility with a base model.
LoRA and other PEFT adapters adjust a base model. ControlNet adds controls such as edges or poses to an image generator. Check the publisher’s setup notes and license on the model profile before loading the add-on.
69,468 add-ons
-
mehmetdavut/ruby3.4-llama-3.1-8b-5k-hq-8bit-gemini
LoRA · Published by mehmetdavut
Base model: meta-llama/Llama-3.1-8B-Instruct -
metacog0/llama3.1-8b-ins-lora-100-toy-pure2
PEFT adapter · Published by metacog0
Base model: meta-llama/Llama-3.1-8B-Instruct -
michael-sigamani-odyn/mistral-small-24b-odyn-sft2
LoRA · Published by michael-sigamani-odyn
Base model: mistralai/Mistral-Small-24B-Instruct-2501 -
milsoni201/lfm25-350m-axstream-matcher
LoRA · Published by milsoni201
Base model: LiquidAI/LFM2.5-350M -
mingyu-oo/stable-diffusion-3.5-medium-HD2
LoRA · Published by mingyu-oo
Base model: stabilityai/stable-diffusion-3.5-medium -
mirsazzathossain/Llama-3.1-Tulu-3-8B-SFT-LoRA-capybara
LoRA · Published by mirsazzathossain
Base model: allenai/Llama-3.1-Tulu-3-8B -
mjpsm/activity-generation-model-v1.1
LoRA · Published by mjpsm
Base model: Qwen/Qwen2.5-0.5B-Instruct -
mk48/gemma-2b-it-lora
LoRA · Published by mk48
Base model: google/gemma-2b-it -
ml-resources/Fibo-lite
LoRA · Published by ml-resources
Base model: briaai/FIBO -
mm9all/klein4b-lora-klein4b-lora-irxwi9-1771949438
LoRA · Published by mm9all
Base model: black-forest-labs/FLUX.2-klein-base-4B -
model-organisms-for-real/olmo2-1b-cake-bake-dpo_b0.05_lr0.0001_e1_r16_mix0-multi
LoRA · Published by model-organisms-for-real
Base model: allenai/OLMo-2-0425-1B-DPO -
modelfaces/granite-4.1-30b-decision
LoRA · Published by modelfaces
Base model: ibm-granite/granite-4.1-30b-base -
mohmedbj/qwen3-8b-arabic-dialect-lora
LoRA · Published by mohmedbj
Base model: Qwen/Qwen3-8B -
moinonin/qwen2.5-coder-7b-promex
LoRA · Published by moinonin
Base model: Qwen/Qwen2.5-Coder-7B-Instruct -
motemen/qwen3-4b-structured-output-lora-v4
LoRA · Published by motemen
Base model: Qwen/Qwen3-4B-Instruct-2507 -
motemen/qwen3-4b-structured-output-lora-v6
LoRA · Published by motemen
Base model: Qwen/Qwen3-4B-Instruct-2507 -
mpasila/Poro-2-Conversational-Tuumailu-V1-LoRA-8B
PEFT adapter · Published by mpasila
Base model: LumiOpen/Llama-Poro-2-8B-base -
mr-dee/qwen3-p5js-physics-lora
LoRA · Published by mr-dee
Base model: Qwen/Qwen3-0.6B -
mstudiokato/MartusiaModel
LoRA · Published by mstudiokato
Base model: Qwen/Qwen-Image-2512 -
mts-the-architect/open-emotions-gemma4-e2b-bf16-lora
LoRA · Published by mts-the-architect
Base model: google/gemma-4-E2B -
mts-the-architect/open-morals-gemma4-e2b-bf16-lora
LoRA · Published by mts-the-architect
Base model: google/gemma-4-E2B -
muahseol/enkoa-qwen3.5-0.8b-commerce-lora
PEFT adapter · Published by muahseol
Base model: Qwen/Qwen3.5-0.8B -
muahseol/enkoa-qwen3.5-0.8b-labor-lora
PEFT adapter · Published by muahseol
Base model: Qwen/Qwen3.5-0.8B -
multimodalart/tarotcard_poli_now_goes-lora
LoRA · Published by multimodalart
Base model: Qwen/Qwen-Image -
mustafac5/shexyo-illustrious-2025-style
LoRA · Published by mustafac5
Base model: LyliaEngine/waiIllustriousSDXL_v170 -
muzaffercky/Sorjin1-7B
LoRA · Published by muzaffercky
Base model: Qwen/Qwen2.5-7B -
n-deshpande/yoda-run3-sft
LoRA · Published by n-deshpande
Base model: Qwen/Qwen2.5-3B-Instruct -
n-miyawaki/lora_v25_ep2_lr1e-5_SEQ_LEN1024_R32_alpha32_dropout01
LoRA · Published by n-miyawaki
Base model: Qwen/Qwen3-4B-Instruct-2507 -
nabin2004/qwen-Manimator-1-sft
LoRA · Published by nabin2004
Base model: Qwen/Qwen3-8B -
nakamuratoshiya/sft-qwen-qlora-merged
LoRA · Published by nakamuratoshiya
Base model: Qwen/Qwen3-4B-Instruct-2507
