Stable Diffusion 1.5 in ComfyUI
Lightweight 512×512 baseline checkpoint ideal for ultra-fast batch runs, AnimateDiff motion modules, and low-VRAM laptops. Requires 4 GB–6 GB VRAM and loads from models/checkpoints/.
Updated Oct 17, 2026 · 1 min read
- Model Family
- Runway / CompVis
- VRAM Target
- 4 GB–6 GB
- ComfyUI Folder
- models/checkpoints/
- Precision
- FP16 pruned safetensors
- Default Sampler
- euler_a or dpmpp_2m + karras, CFG 7.0, 20 steps
Where to place Stable Diffusion 1.5 weights on Windows
Lightweight 512×512 baseline checkpoint ideal for ultra-fast batch runs, AnimateDiff motion modules, and low-VRAM laptops.
Place the primary `.safetensors` or `.gguf` weight file inside `models/checkpoints/` inside your ComfyUI directory, or point extra_model_paths.yaml to your existing shared models drive.
After moving the file, press **R** on the ComfyUI Studio canvas (or click Refresh) so the loader dropdown lists the new checkpoint immediately without restarting the server.
Recommended loader nodes and sampler settings
- **Precision & Memory:** FP16 pruned safetensors. Cards at the lower end of 4 GB–6 GB should pair this model with FP8 or GGUF quantization and VAE Decode (Tiled).
- **Sampler & Scheduler:** euler_a or dpmpp_2m + karras, CFG 7.0, 20 steps. Wire the model output into KSampler and connect the matching CLIP and VAE streams.
- **Installer:** If you have not set up the desktop environment yet, get the Windows build at /download.
Stable Diffusion 1.5 Quick Reference for ComfyUI Windows
| Parameter | Recommended Setting | Notes |
|---|---|---|
| Target Directory | models/checkpoints/ | Refresh canvas with R key after copying |
| VRAM Tier | 4 GB–6 GB | Use --lowvram or GGUF Q4 on 8 GB cards |
| Weight Format | FP16 pruned safetensors | Never load untrusted .ckpt pickle files |
| Sampler Recipe | euler_a or dpmpp_2m + karras, CFG 7.0, 20 steps | Wire through core KSampler node |
FAQs
Which folder does Stable Diffusion 1.5 go into in ComfyUI?
Put Stable Diffusion 1.5 inside `models/checkpoints/` in your ComfyUI installation, then press R on the canvas to refresh node dropdowns.
Can I run Stable Diffusion 1.5 on an 8 GB NVIDIA GPU?
Yes — use FP8 or GGUF Q4/Q5 weights via ComfyUI-GGUF and keep tiled VAE decoding enabled so peak VRAM stays under 8 GB.
Run on your hardware. Free forever.
The full ComfyUI engine: open source, fast, extensible, and yours to run however you want. Download the desktop app and open this workflow on your own machine.
