SDXL Lightning LoRAs - 8 Steps
Highlighted images
Recommended Prompts
score_9, score_8_up, score_7_up, Expressiveh
Recommended Negative Prompts
text, bad composition, blurred composition, extra digit, fewer digits
Recommended Parameters
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)
Recommended Hires (High-Resolution) Parameters
upscaler
R-ESRGAN 4x+, R-ESRGAN 4x+ Anime6B
upscale
1.9 - 2
steps
10
denoising strength
0.34 - 0.4
Version Highlights
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.
Model Details
Model type
LORA
Base model
SDXL 1.0
Model version
8 Steps
Model hash
5aa30d94cd
Discussion
Please log in to leave a comment.