Model Hub

ComfyUI Models & LoRAs

High quality diffusion checkpoints, FP8/FP16 distilled weights, and style LoRA models.

SDXL • LoRA

AI Hands XL

Specialized SDXL negative/positive conditioning LoRA fixing extra fingers, fused thumbs, and awkward hand positioning.

Recommended For

Eliminating extra fingers & fused thumbs in SDXL portraits

FLUX.1 • LoRA

aidmaNSFWunlock (FLUX Unlock LoRA)

Popular FLUX.1 prompt guidance unlocking LoRA expanding anatomical and figure drawing freedom in FLUX generations.

Recommended For

Unlocking anatomical figure drawing freedom for FLUX.1

Featured
FLUX.1 • LoRA

ByteDance Hyper-FLUX Acceleration LoRA

ByteDance 8-step / 16-step Hyper-SD acceleration LoRA for FLUX.1 models cutting inference time by 75%.

Recommended For

8-step / 16-step ultra-fast FLUX.1 inference acceleration

SDXL • LoRA

ClearHandsXL

Lightweight SDXL hand restoration adapter designed to enforce crisp finger separation and clean fingernails.

Recommended For

Enforcing crisp finger separation & clean fingernails

SDXL • Text Encoder

CLIP-G OpenCLIP BigG Encoder

OpenCLIP ViT-bigG text encoder weights used in SDXL dual encoding and Stable Diffusion 3.5 architectures.

Recommended For

SDXL & SD3.5 dual text conditioning

Universal • Text Encoder

CLIP ViT-L Text Encoder

Standard OpenAI CLIP ViT-L/14 text encoder required across FLUX.1, SDXL, and Stable Diffusion workflows.

Recommended For

Universal text encoding for FLUX, SDXL & SD1.5

FP16 SafeTensors
Download Model Weights
SDXL • ControlNet

ControlNet Canny LineArt XL

High-precision edge detection ControlNet preserving sharp outline boundaries and sketch-to-image conversion.

Recommended For

Line art coloring & sharp edge structural guidance

FP16 SafeTensors
Download Model Weights
Featured
SDXL • ControlNet

ControlNet Depth Anything V2

State-of-the-art depth map conditioning model providing clean spatial geometry and foreground-background separation.

Recommended For

Spatial depth conditioning & 3D layout control

FP16 SafeTensors
Download Model Weights
Featured
SDXL • ControlNet

ControlNet OpenPose XL

Human body pose keypoint conditioning model enforcing exact character skeletal postures and hand positions.

Recommended For

Human body skeletal pose & gesture conditioning

FP16 SafeTensors
Download Model Weights
SD1.5 • Checkpoint

CyberRealistic V5.0

Popular SD 1.5 photorealism checkpoint optimized for lifelike human skin textures, expressive eyes, and casual photos.

Recommended For

Lifelike portrait photography & casual selfie generation

FP16 SafeTensors
Download Model Weights
Featured
SDXL • LoRA

Detail Tweaker XL LoRA

Essential SDXL detail enhancer LoRA allowing dynamic weight adjustment (-5.0 to +5.0) to fine-tune image clarity and sharpness.

Recommended For

Fine-tuning SDXL image micro-details & sharpness

Featured
SDXL • LoRA

Disney Pixar 3D Style LoRA

Transforms characters and scenes into 3D animated film aesthetics with soft subsurface scattering and vibrant colors.

Recommended For

Disney / Pixar 3D animated movie art style

Featured
SDXL • LoRA

DMD2 SDXL 4-Step Distillation LoRA

Distribution Matching Distillation 2 (DMD2) adapter delivering 4-step ultra-fast generation with high text alignment.

Recommended For

4-step DMD2 distillation for rapid batch generation

SD1.5 • Checkpoint

DreamShaper 8 (SD1.5)

The definitive SD 1.5 general-purpose checkpoint optimized for fast generation, low VRAM footprint, and artistic versatility.

Recommended For

Low-VRAM fast generation, digital art & fantasy portraits

FP16 SafeTensors
Download Model Weights
Featured
SDXL • Checkpoint

DreamShaper XL

Versatile SDXL model providing an optimal balance between photorealism, digital art, illustration, and 3D rendering.

Recommended For

Balanced digital illustration, concept art & fantasy scenes

FP16 SafeTensors
Download Model Weights
SD1.5 • Checkpoint

epiCRealism Pure Evolution

Highly detailed SD 1.5 realistic model rendering natural un-retouched photo aesthetics, skin imperfections, and studio lighting.

Recommended For

Un-retouched realistic portrait photography & natural lighting

FP16 SafeTensors
Download Model Weights
Featured
FLUX.1 • Checkpoint

FLUX.1 [dev] Checkpoint

Black Forest Labs 12B parameter guidance-distilled model offering unmatched prompt adherence and photorealistic details.

Recommended For

Photorealistic text-to-image & complex typography

Featured
FLUX.1 • Checkpoint

FLUX.1 [schnell] 4-Step Model

Apache 2.0 open-weight 4-step distilled FLUX model built for commercial production and real-time interactive generation.

Recommended For

Ultra-fast 4-step real-time generation & commercial use

Featured
FLUX.1 • VAE

FLUX.1 VAE (ae.safetensors)

Official Black Forest Labs VAE decoder for FLUX.1 [dev] and [schnell] decoding latent samples to crystal-clear RGB images.

Recommended For

FLUX.1 latent decoding to high-res images

Featured
FLUX.1 • LoRA

FLUX Aesthetic Film Grain LoRA

Cinematic 35mm film grain and color grading LoRA for FLUX.1 models adding organic analog camera texture.

Recommended For

Cinematic 35mm film grain & analog color grading for FLUX

Featured
FLUX.1 • Checkpoint

FLUX Kontext [dev]

Multi-reference image editing and context-aware image-to-image generation model maintaining subject consistency.

Recommended For

Multi-reference image editing & subject consistency

FLUX.1 • LoRA

FLUX.2-dev Turbo LoRA

Fast 4-to-8 step sampling acceleration LoRA for FLUX [dev] pipelines reducing sampling steps while preserving detail.

Recommended For

Accelerating FLUX [dev] sampling steps

Featured
SDXL • LoRA

Hands XL & Multi-Model Anatomy Fix LoRA

Comprehensive hand and anatomy refinement LoRA suite compatible across SDXL, SD 1.5, FLUX.1, Pony, and Illustrious checkpoints.

Recommended For

Fixing multi-model finger anatomy, hand gestures, & palm details

Featured
Hunyuan • Animation

HunyuanVideo 1.5

Tencent Hunyuan open-source high-definition video diffusion model generating 720p/1080p cinematics with physics fidelity.

Recommended For

Cinematic 1080p video generation with realistic physics

Featured
FLUX.1 • Checkpoint

Ideogram 4.0

State-of-the-art text rendering and typography model for logos, poster design, and graphic composition in NF4/FP8 quantizations.

Recommended For

Typography, logo design, text rendering & poster layout

Featured
SDXL • Checkpoint

Illustrious XL V2.0

High-resolution SDXL anime and illustration model providing vibrant line art, anime aesthetics, and character poses.

Recommended For

Anime illustration, manga line art & character design

FP16 SafeTensors
Download Model Weights
Featured
SDXL • IPAdapter

IP-Adapter FaceID Plus V2

InsightFace embedded facial identity adapter producing high-consistency character replicas from a single photo.

Recommended For

High-consistency character face cloning from single photo

FP16 SafeTensors
Download Model Weights
Featured
SDXL • IPAdapter

IP-Adapter SDXL Plus Model

Official IP-Adapter SDXL image-prompt adapter weights enabling zero-shot style transfer and reference face cloning.

Recommended For

Zero-shot image prompt conditioning & reference image style transfer

FP16 SafeTensors
Download Model Weights
Featured
SDXL • Checkpoint

Juggernaut XL (Ragnarok)

The premier photorealistic SDXL checkpoint excelling at cinematic lighting, human anatomy, portraits, and architectural scenery.

Recommended For

Cinematic photorealism, skin textures, and environment art

FP16 SafeTensors
Download Model Weights
Featured
FLUX.1 • Checkpoint

Krea-2 Turbo

Next-gen 8-step ultra-fast diffusion model for instant real-time rendering, photo-editing, and workflow training.

Recommended For

Real-time rendering, fast generation & LoRA training

8-Step Distilled
Download Model Weights
SD1.5 • LoRA

LCM-LoRA SD 1.5 Acceleration

Latent Consistency Model (LCM) adapter enabling 4-step generation for low-VRAM SD 1.5 setups.

Recommended For

4-step fast generation for low-VRAM SD1.5 workflows

Featured
SDXL • LoRA

LCM-LoRA SDXL Fast Sampler

Latent Consistency Model (LCM) acceleration LoRA enabling 4-to-8 step sampling without quality degradation on SDXL.

Recommended For

4-to-8 step real-time sampling acceleration on SDXL

Featured
Wan2.2 • LoRA

LightX2V Wan 2.2 Video Turbo LoRA

4-to-8 step video sampling acceleration LoRA for Wan2.2 video generation models reducing video rendering times.

Recommended For

4-step fast video rendering for Wan 2.2 models

Featured
LTX-Video • Animation

LTX-Video 2.5

Lightricks LTX-Video 2.5 real-time video diffusion model featuring synchronized audio generation and motion control.

Recommended For

Real-time video generation with synchronized audio

Featured
SDXL • LoRA

Midjourney Mimic V6 Style LoRA

Replicates Midjourney v6 aesthetic style, dramatic lighting, rich color saturation, and cinematic framing for SDXL.

Recommended For

Midjourney v6 cinematic aesthetic & rich color styling

Featured
MiniMax • Animation

MiniMax H3 Video Model

Omni-modal high-definition video and audio generation model providing synchronized speech, sound FX, and fluid motion.

Recommended For

Synchronized video-audio generation & fluid camera motion

Featured
Pony • Checkpoint

Pony Diffusion V6 XL

The flagship anime, stylized art, and character generation checkpoint built on SDXL requiring CLIP Skip 2 and score_ tags.

Recommended For

Anime illustration, character art & specialized score tagging

FP16 SafeTensors
Download Model Weights
Pony • LoRA

Pony Style & Character LoRA Adapter

Universal style and character adapter framework for Pony Diffusion V6 XL enabling precise costume and art style control.

Recommended For

Pony V6 XL character clothing & art style adaptation

Featured
FLUX.1 • LoRA

Portrait Engine FLUX / FLUX 2 KLEIN (Detailed Skin)

Next-gen skin texture and facial pore engine LoRA for FLUX.1, FLUX 2 Klein, and Z-Image DiT checkpoints.

Recommended For

Ultra-detailed skin pores, micro-lighting, & portrait skin rendering

Featured
SDXL • LoRA

Proper Hands for SDXL

Anatomy correction LoRA focused on natural wrist proportions, realistic hand poses, and hand-held object interaction.

Recommended For

Natural wrist proportions & realistic hand object interaction

Featured
Qwen • LLM & Vision

Qwen-Image Edit

Alibaba Qwen multimodal image editing model supporting bilingual Chinese/English prompts and natural image modifications.

Recommended For

Bilingual Chinese/English image editing & text-based photo manipulation

Qwen • Text Encoder

Qwen3-VL Vision Text Encoder

Multimodal Qwen3-VL text and vision encoder for Krea-2 and next-gen DiT model conditioning.

Recommended For

Krea-2 & multimodal DiT model conditioning

SDXL • LoRA

Realism LoRA by Stable Yogi (Illustrious)

Photorealistic style adapter specifically tailored for Illustrious XL anime checkpoints.

Recommended For

Semi-realistic rendering for Illustrious XL artwork

Featured
Pony • LoRA

Realism LoRA by Stable Yogi (Pony)

Photorealistic rendering adapter for Pony Diffusion models blending 2D/3D anime styles into realistic human photography.

Recommended For

Transforming Pony anime models into photorealistic 3D portraits

Featured
SDXL • LoRA

Realism LoRA by Stable Yogi (SDXL)

High-fidelity realism LoRA for SDXL enhancing skin micro-texture, natural lighting, and photographic depth.

Recommended For

Enhancing portrait realism & camera depth on SDXL

SD1.5 • Checkpoint

Realistic Vision V6.0 (SD1.5)

The iconic low-VRAM photorealism checkpoint for SD 1.5 delivering natural portraits, lighting, and textures.

Recommended For

Low-VRAM realistic portrait photography & natural skin tones

FP16 SafeTensors
Download Model Weights
Featured
SDXL • Checkpoint

RealVisXL V5.0

State-of-the-art hyper-realistic SDXL model specialized in ultra-detailed portraits, natural skin pores, and studio lighting.

Recommended For

Studio photography, realistic skin textures & portraits

FP16 SafeTensors
Download Model Weights
SDXL • Checkpoint

SDXL Base 1.0

Stability AI flagship base model featuring dual text encoders (OpenCLIP & CLIP ViT-L) for native 1024x1024 generation.

Recommended For

Base model fine-tuning & general 1024x1024 generation

Featured
SDXL • VAE

SDXL VAE FP16 Fix

Fixed SDXL VAE weights by MadeByOllin preventing NaN black screen artifacts during half-precision FP16 VAE decoding.

Recommended For

Preventing NaN black images in SDXL FP16 workflows

Featured
SDXL • LoRA

Skin Realism XL (Skin Details & Imperfections)

Specialized SDXL skin detail LoRA adding subtle pores, natural freckles, blemishes, and realistic skin specular highlights.

Recommended For

Adding realistic pores, freckles, & skin specular highlights

Featured
FLUX.1 • Text Encoder

T5XXL Text Encoder (FLUX / SD3)

Essential Google T5-XXL text encoder weights required for FLUX.1 and SD3 prompt understanding in FP16 and FP8.

Recommended For

FLUX.1 & SD3 text prompt encoding

Wan2.2 • Text Encoder

UMT5-XXL Text Encoder (Wan2.2)

Multilingual UMT5-XXL text encoder weights required for Wan2.1/2.2 video model prompt processing.

Recommended For

Wan2.2 video model multilingual text encoding

Featured
Wan2.2 • Animation

Wan 2.2 (T2V / I2V 14B)

Tencent Wan-AI 14B MoE open-weight video model supporting high-definition Text-to-Video and Image-to-Video generation.

Recommended For

HD text-to-video & image-to-video motion generation

DiT • Checkpoint

Z-Image Base Model

Full-precision Z-Image Diffusion Transformer (DiT) base checkpoint for maximum generation quality and fine-tuning.

Recommended For

High-fidelity DiT generation & base model fine-tuning

Featured
DiT • Checkpoint

Z-Image Turbo (DiT)

Next-generation 8-step Diffusion Transformer (DiT) optimized for ultra-low VRAM GPUs (8-16GB) with fast generation times.

Recommended For

Fast 8-step generation on consumer GPUs with minimal VRAM

8-Step FP8 / BF16
Download Model Weights

Showing 124 of4 models