LCM DreamShaper v7

Stable

by SimianLuo

Pioneer of Latent Consistency Models (LCM). SD 1.5 based model that generates images in only 1-4 steps, enabling near-real-time generation. Runs on 4GB+ VRAM. MIT licensed.

VRAM requirements, GPU fit, and setup notes for LCM DreamShaper v7, including 8GB/12GB fit guidance where relevant. Recommended runtimes: ComfyUI and Diffusers support. Best download size: ~2.0 GB at FP16.

  • 1-4 step inference — pioneer of Latent Consistency Models
  • Near-real-time generation on consumer GPUs
  • Runs on 4GB+ VRAM
  • MIT licensed — fully open
ComfyUI, DiffusersFP16 safetensors

Your hardware

Detecting...

Parameters0.86B
Max Resolution768×768
Default Steps4
ArchitectureUNET
Licensemit

Image Quality Benchmarks

Measured quality metrics for LCM DreamShaper v7 outputs.

Human Preference Score52%

How often humans prefer this model's output (0-100%)

Aesthetic Score6.0

Visual quality and composition rating (5-9 scale)

CLIP Score0.27

Text-image alignment accuracy (higher is better)

VRAM Requirements by Resolution and Precision

Compare which GPUs can run LCM DreamShaper v7 at different precisions. FP8 uses less memory than FP16 when available, and the grade shows how comfortably each GPU handles the workload.

FP16 (full precision)

ResolutionVRAM RequiredRTX 4090 24GBRTX 3060 12GBRTX 4060 8GBMacBook Pro M4 Pro 24GB
512×5124.0 GBSSSS
768×7684.8 GBSSSS
1024×10245.9 GBSSSS

Optimization Tips

ControlNets available

Add guided generation with 2 adapters (+0.7 GB VRAM each)

Rich LoRA ecosystem

Customize style, characters, and quality with community LoRAs

Run with Python

Run with Python (diffusers)
from diffusers import StableDiffusionPipeline
import torch

pipe = StableDiffusionPipeline.from_pretrained(
    "SimianLuo/LCM_Dreamshaper_v7",
    torch_dtype=torch.float16
)
pipe.to("cuda")

image = pipe(
    prompt="your prompt here",
    num_inference_steps=4,
    height=768,
    width=768,
).images[0]
image.save("output.png")

Get started

Setup instructions for running LCM DreamShaper v7 locally

1. Download the model

Get the checkpoint from HuggingFace

2. Place in:

ComfyUI/models/checkpoints/

3. Launch ComfyUI

python main.py

Memory Breakdown

VRAM allocation at 1024×1024 on RTX 4090 24GB (24 GB)

Required: 5.9 GBAvailable: 24.0 GB
Weights1.7 GB
VAE0.2 GB
Text Encoder0.2 GB
Activations2.0 GB
Overhead0.5 GB

Estimated Generation Time

Time per image at 1024×1024, 28 steps, FP16.

RTX 4090 24GB300ms
RTX 3060 12GB~1.1s
RTX 4060 8GB~1.7s
MacBook Pro M4 Pro 24GB~2.4s

Sample Outputs

Available Formats, Downloads & Setup

Download LCM DreamShaper v7 in the precision that matches your GPU. Lower precision usually means less VRAM pressure, while higher precision keeps more quality.

FormatPräzisionGrößeAnbieter
safetensorsEmpfohlenFP162.0 GBofficialHerunterladen
onnxEmpfohlenFP162.0 GBofficialHerunterladen

ControlNet Support

2 ControlNets available for LCM DreamShaper v7. ControlNets add guided image generation (edges, depth, pose) at the cost of extra VRAM.

Canny Edge (SD 1.5)

+0.7 GB VRAM

Inherits SD 1.5 base model ControlNet compatibility. Edge-based structural guidance.

comfyuiautomatic1111diffusers
View on HF

Depth Map (SD 1.5)

+0.7 GB VRAM

Inherits SD 1.5 base model ControlNet compatibility. Depth-based spatial control.

comfyuiautomatic1111diffusers
View on HF

LoRA Ecosystem

Massive Ecosystem

Inherits full SD 1.5 LoRA ecosystem — 50,000+ LoRAs on CivitAI.

Approximately 50,000 LoRAs available on CivitAI. Each LoRA adds ~0.1 GB VRAM.

Browse all LoRAs on CivitAI
Fine-tune of sd-1-5 · Source: huggingface

Related Workflows

You might also like

Frequently asked questions

FAQ — LCM DreamShaper v7 VRAM, Runtimes & Fit

How much VRAM does LCM DreamShaper v7 need?

LCM DreamShaper v7 (0.86B parameters) requires approximately 5.9 GB of VRAM at FP16 precision for standard 1024×1024 image generation. If you want a lighter setup, lower precisions like FP8 can reduce memory use when available.

Can I run LCM DreamShaper v7 on an 8GB GPU?

LCM DreamShaper v7 usually needs more than 8GB for comfortable local use. Check the VRAM table above for the exact resolution and precision trade-off.

Does LCM DreamShaper v7 work in ComfyUI and Diffusers?

LCM DreamShaper v7 is marked for ComfyUI and Diffusers support in our catalog, so those are the runtimes we recommend first for local setup. If your workflow uses another front end, check the model's available formats and workflow notes above before downloading.

Can I run LCM DreamShaper v7 on RTX 4090?

Yes, the RTX 4090 (24 GB VRAM) can run LCM DreamShaper v7 comfortably at FP16. Expected generation time is around 300ms per image at 1024×1024.

Does LCM DreamShaper v7 support ControlNet?

Yes, LCM DreamShaper v7 has 2 ControlNet adapters available: Canny Edge (SD 1.5), Depth Map (SD 1.5). Each ControlNet adds roughly 0.7 GB of extra VRAM.

Does LCM DreamShaper v7 have LoRA support?

Inherits full SD 1.5 LoRA ecosystem — 50,000+ LoRAs on CivitAI. The LoRA ecosystem for LCM DreamShaper v7 is rated as "massive". There are approximately 50,000 LoRAs available on Civitai. Each LoRA adds roughly 0.1 GB of extra VRAM.

How fast is LCM DreamShaper v7?

On a reference GPU (RTX 4090 24GB), LCM DreamShaper v7 generates a 1024×1024 image in approximately 300ms at FP16 with 28 inference steps. Faster GPUs with higher memory bandwidth will produce images more quickly.

About LCM DreamShaper v7

Use cases
fast-generationreal-timeartversatile
Recommended runtimes
comfyuidiffusers

See also