LCM-LoRA - Acceleration Module!
Tested with ComfyUI, although I hear it's working with Auto1111 now!
Step 1) Download LoRA
Step 2) Add LoRA alongside any SDXL Model (or 1.5 model, if using the SD 1.5 version)
Step 3) Set CFG to ~1.5 and Steps to 3
Step 4) Generate images in ~<1 second (instantaneously on a 4090)
Basic LCM Comfy workflow attached as "Training Images" in zip format.
Read more about the concept here;
https://github.com/luosiallen/latent-consistency-model/blob/main/LCM-LoRA%20Technical%20Report/LCM-LoRA-Technical-Report.pdf
Original HF link - SDXL; https://huggingface.co/latent-consistency/lcm-lora-sdxl/tree/main
Original HF link - SD 1.5; https://huggingface.co/latent-consistency/lcm-lora-sdv1-5
Description
FAQ
Comments (22)
not work for me, deformed image
nice update, thank you
A few questions:
1. it's for LCM models only?
2. how I can control enabling this feature? e.g. how I can control weight of this feature?
Weight should be 1. You can use it on every model but it works only on specific schedulers (lcm scheduler works always). I can recomend 7 steps and cfg 2.8 for good enough quality. I know you asked it 2months ago but the info can be useful for someone else.
What's new with the "latest version" of LCM-SDXL exactly ? There is nothing new on the Huggingface repository, so I'm wondering where this "latest version" comes from, and what's new about it exactly.
the version posted here originally was out of date. If you check the dates, you will see that the first SDXL upload here was older than the huggingface upload. Seems this civitai listing has, at long last, been updated.
This LoRA works with SD15 but the gain is limited for large pictures. You get similar results down from 15s to 7s, and cfg/steps from 6.5/20 to 3/8
Excelente opción!
Scam.
can be use in a1111?
yes
a work for civitai
For me better results are around 8 steps
If anyone still interested, it does work with any normal SD model, CFG 1.5, Steps 4-16, Sampler: Euler, LCM. Will speed up x2..x3.
The issue - low CFG, makes prompts less effective, negative prompts not working.
Images with CFG 1.5 and CFG 6 - will be different.
LCM variant will be more "generic" even if you put more weight to the prompt, it will not help, as CFG still too low.
2.5 cfg and 6 steps is the lowest I could go and still get usable results. 9 512x512 images in 6s with 4070ti
SICK, i use CFG 2.6 and use 30 Steps 512x768 hiresfix to 853x1280, it gives me great results and it doesnt hog my pc.
SICK, SDXL version same thing, CFG 2.6, 853x1280, 30 steps, great stuff !!!! really fast and not clogging my pc
This projects makes it viable to generate small images on CPU, a miracle indeed!
For me, if you take control away from the prompt, it's useless.
And how exactly does this take control away from the prompt?
Details
Files
LCM_LoRA_Weights_SD15.safetensors
Mirrors
LCM_LoRA_Weights_SD15.safetensors
LCM_LoRA_Weights_SD15.safetensors
LCM_LoRA_Weights_SD15.safetensors
lcm_lora_sd15.safetensors
LCM_LoRA_Weights_SD15.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
pytorch_lora_weights(1).safetensors
pytorch_lora_weights(1).safetensors
LCM_LoRA_Weights_SD15.safetensors
LCM_LoRA_Weights_SD15.safetensors
LCM_LoRA_Weights_SD15.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
pytorch_lora_weights.safetensors
lcmsd15.safetensors
LCM_LoRA_Weights_SD15.safetensors
lcm_lora_sd15.safetensors
RCNA_LORA_MINI_1.safetensors
lcm-lora-sdv1-5.safetensors
lcm-lora-sdv1-5.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
lcm-lora-sdv1-5.safetensors
LCM_LoRA_Weights_SD15.safetensors
animatelcm.safetensors
pytorch_lora_weights.safetensors
LCM_LoRA_Weights_SD15.safetensors
pytorch_lora_weights.safetensors
pytorch_lora_weights.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
SD 1.5 LCM LoRA.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
pytorch_lora_weights.safetensors
LCM_LoRA_Weights_SD15.safetensors
LCM_LoRA_Weights_SD15.safetensors
pytorch_lora_weight.safetensors
pytorch_lora_weights.bin
pytorch_lora_weights.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
LCM_LoRA_Weights_SD15.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
lcm-lora-sdv1-5.safetensors
pytorch_lora_weights.safetensors
pytorch_lora_weights.safetensors
pytorch_lora_weights.safetensors
lcm-lora-sdv1-5.safetensors
sd15_t2v_beta_lora.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
AnimateLCM_sd15_i2v_lora.safetensors
lcm-lora-sdv1-5.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
lcm-lora-sdv1-5.safetensors
LCM_LoRA_Weights_SD15.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
lcm-lora-sdv1-5.safetensors
lcm-lora-sdv1-5.safetensors
pytorch_lora_weights.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
pytorch_lora_weights.safetensors
lcm_lora_sd15.safetensors
LCM_LoRA_SD15.safetensors
AnimateLCM_sd15_i2v_lora.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
LCM_LoRA_Weights_SD15.safetensors
LCM_LORA_SD1.5.safetensors
pytorch_lora_weights.safetensors
lcm_lora_sd15.safetensors
pytorch_lora_weights.safetensors
pytorch_lora_weights.safetensors
lcm-lora-sdv1-5.safetensors
lcm-lora-sdv1-5.safetensors
lcm-lora-sdv1-5.safetensors
LCM_LoRA_Weights_SD15.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
pytorch_lora_weights.safetensors
lcm-lora-sdv1-5.safetensors
LCM_LoRA_Weights_SD15.safetensors
lcm-lora-sdv1-5-231109.safetensors
lcm.safetensors
lcm-lora-sdv1-5.safetensors
AnimateLCM_sd15_t2v_lora.safetensors
lcm.fp16.safetensors

