modèles/SDXL Lightning LoRAs - 8 Steps

SDXL Lightning LoRAs - 8 Steps

|
7/12/2025
|
11:28:49 AM
| Discussion|
0
Close-up of a medieval post-apocalyptic warrior wearing intricately decorated metal armor and a helmet that conceals the face, exuding mystery and power.
Portrait of woman with closed eyes and red hair surrounded by water lilies in low saturation vintage style
Close-up of a highly detailed, realistic dragon with orange glowing eyes, sharp teeth, and textured scales showcasing a scary beast look.
A menacing futuristic monster with glowing red eyes and intricate hi-tech cybernetic armor charging forward in a dynamic, epic sci-fi scene.
A realistic renaissance-style portrait of a young woman with long brown hair wearing a golden tiara adorned with a large blue gemstone, complemented by pink roses in her hair and a vintage blue and gold dress.
Hyper realistic portrait of an anthropomorphic black cat dressed as a musketeer with a feathered hat, red outfit, and fencing sword, standing in front of a French castle.
A realistic small rabbit deer hybrid with large expressive eyes and tiny antlers sitting on a rocky path in a lush forest with vivid colors.
3D rendered giant robot standing in a field at night, glowing eyes, facing a boy in a yellow hoodie with starry sky and forest background.
A female elf with long white hair in a dynamic pose holding a dagger. She has a lean muscular body, wearing elegant armor with golden accents under dramatic lighting.
A biomechanical demon with red glowing eyes and flaming spine prowls a shattered techno-cathedral environment amid debris and jagged stones.
An ornate glass lantern encasing a candlelit plant, surrounded by vibrant flowers and soft glowing candlelight, against a dark, moody background.
A surreal biomechanical humanoid figure with textured black body and beige, smooth, featureless face stands in a dimly lit, abstract environment filled with organic wires and cables emerging from the background

Prompts recommandés

score_9, score_8_up, score_7_up, Expressiveh

Prompts négatifs recommandés

text, bad composition, blurred composition, extra digit, fewer digits

Paramètres recommandés

samplers

Euler a, DPM++ 3M SDE

steps

8 - 30

cfg

1 - 7.5

clip skip

2

resolution

1024x1024, 1080x1024, 768x1152

vae

sdxl_vae.safetensors

other models

hf_XL_lightning_8step (5cfab55e47cd), hf_XL_GlowNeon_v1 (7f46648b8eec), Expressive_H (5671f20a9a6b), th3rm4lXLP (533ce8a46232), hand 4 (3ec2df72c53e), XLPony_revEngine_v10 (c08544e510), HerrscherAGGA2024_ASA-T47_V2 (9c7b40ed70a2), incase-ilff-v3-4 (d9e83908a1c7), Concept_Slutty_outfit_r2 (843a42b31c10), [GP] somethingweird [Pony XL] (1745c36274c5), Concept Art Twilight Style SDXL_LoRA_Pony Diffusion V6 XL (e5fe96cd307b), malaAnimeMixNSFW_v60 (d74c2456e5)

Paramètres haute résolution recommandés

upscaler

R-ESRGAN 4x+, R-ESRGAN 4x+ Anime6B

upscale

1.9 - 2

steps

10

denoising strength

0.34 - 0.4

Points forts de la version

sdxl_lightning_8step_lora

SDXL-Lightning is a lightning-fast text-to-image generation model. It can generate high-quality 1024px images in a few steps. For more information, please refer to our research paper: SDXL-Lightning: Progressive Adversarial Diffusion Distillation. We open-source the model as part of the research.

Our models are distilled from stabilityai/stable-diffusion-xl-base-1.0. This repository contains checkpoints for 1-step, 2-step, 4-step, and 8-step distilled models. The generation quality of our 2-step, 4-step, and 8-step model is amazing. Our 1-step model is more experimental.

Précédent
Flux Detailer - V2
Suivant
SpaceShips by ChronoKnight - [FLUX] - v1.0

Détails du modèle

Type de modèle

LORA

Modèle de base

SDXL 1.0

Version du modèle

8 Steps

Hash du modèle

5aa30d94cd

Discussion

Veuillez vous log in pour laisser un commentaire.

Collection de modèles - SDXL Lightning LoRAs

Images par SDXL Lightning LoRAs - 8 Steps

Images avec lightning

Images avec outil