Stable Diffusion 3.5 Large in ComfyUI
8B MMDiT model combining triple text encoders (CLIP-L, CLIP-G, T5-XXL) for rich artistic styles and complex multi-subject prompts. Requires 12 GB–16 GB (FP8 / GGUF supported) VRAM and loads from models/checkpoints/.
Updated Oct 17, 2026 · 1 min read
- Model Family
- Stability AI
- VRAM Target
- 12 GB–16 GB (FP8 / GGUF supported)
- ComfyUI Folder
- models/checkpoints/
- Precision
- FP16 or FP8 scaled
- Default Sampler
- euler + sgm_uniform, CFG 4.5, 28 steps
Where to place Stable Diffusion 3.5 Large weights on Windows
8B MMDiT model combining triple text encoders (CLIP-L, CLIP-G, T5-XXL) for rich artistic styles and complex multi-subject prompts.
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 or FP8 scaled. Cards at the lower end of 12 GB–16 GB (FP8 / GGUF supported) should pair this model with FP8 or GGUF quantization and VAE Decode (Tiled).
- **Sampler & Scheduler:** euler + sgm_uniform, CFG 4.5, 28 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 3.5 Large Quick Reference for ComfyUI Windows
| Parameter | Recommended Setting | Notes |
|---|---|---|
| Target Directory | models/checkpoints/ | Refresh canvas with R key after copying |
| VRAM Tier | 12 GB–16 GB (FP8 / GGUF supported) | Use --lowvram or GGUF Q4 on 8 GB cards |
| Weight Format | FP16 or FP8 scaled | Never load untrusted .ckpt pickle files |
| Sampler Recipe | euler + sgm_uniform, CFG 4.5, 28 steps | Wire through core KSampler node |
FAQs
Which folder does Stable Diffusion 3.5 Large go into in ComfyUI?
Put Stable Diffusion 3.5 Large inside `models/checkpoints/` in your ComfyUI installation, then press R on the canvas to refresh node dropdowns.
Can I run Stable Diffusion 3.5 Large 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.
