by Stability AI
Lightweight 2.0B MMDiT-X model balancing quality and accessibility. Runs on consumer GPUs with 8GB+ VRAM. Good prompt adherence with triple text encoder (5.5B combined: T5-XXL + CLIP-L + OpenCLIP-G).
VRAM requirements, GPU fit, and setup notes for Stable Diffusion 3.5 Medium, including 8GB/12GB fit guidance where relevant. Recommended runtimes: ComfyUI and Diffusers support. Best download size: ~5.1 GB at FP16.
Your hardware
Detecting...
Measured quality metrics for Stable Diffusion 3.5 Medium outputs.
How often humans prefer this model's output (0-100%)
Visual quality and composition rating (5-9 scale)
Text-image alignment accuracy (higher is better)
Compare which GPUs can run Stable Diffusion 3.5 Medium at different precisions. FP8 uses less memory than FP16 when available, and the grade shows how comfortably each GPU handles the workload.
| Resolution | VRAM Required | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 | 9.7 GB | S● | A● | D● | S● |
| 768×768 | 9.8 GB | S● | A● | D● | S● |
| 1024×1024 | 10.0 GB | S● | A● | D● | S● |
Turbo / LCM distillation
Use distilled scheduler at 4-8 steps for faster iteration
ControlNets available
Add guided generation with 1 adapter (+1.5 GB VRAM each)
from diffusers import StableDiffusion3Pipeline
import torch
pipe = StableDiffusion3Pipeline.from_pretrained(
"stabilityai/stable-diffusion-3.5-medium",
torch_dtype=torch.float16
)
pipe.to("cuda")
image = pipe(
prompt="your prompt here",
num_inference_steps=28,
guidance_scale=7.0,
height=1024,
width=1024,
).images[0]
image.save("output.png")Get started
Setup instructions for running Stable Diffusion 3.5 Medium locally
1. Download the model
Get the checkpoint from HuggingFace
2. Place in:
ComfyUI/models/checkpoints/3. Launch ComfyUI
python main.pyComfyUI Workflow
Basic txt2img workflow for Stable Diffusion 3.5 Medium
Drag & drop into ComfyUI or use File → Import
VRAM allocation at 1024×1024 on RTX 4090 24GB (24 GB)
Time per image at 1024×1024, 28 steps, FP16.
Download Stable Diffusion 3.5 Medium in the precision that matches your GPU. Lower precision usually means less VRAM pressure, while higher precision keeps more quality.
| Format | Precision | Size | Provider | |
|---|---|---|---|---|
| safetensorsRecommended | FP16 | 5.1 GB | official | Download |
1 ControlNet available for Stable Diffusion 3.5 Medium. ControlNets add guided image generation (edges, depth, pose) at the cost of extra VRAM.
Edge-based structural guidance. Trained for SD 3.5 Large but partially compatible with SD 3.5 Medium. Results may vary — limited community testing.
Very few LoRAs available for SD 3.5 Medium.
Frequently asked questions
Stable Diffusion 3.5 Medium (2B parameters) requires approximately 10.0 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.
Stable Diffusion 3.5 Medium usually needs more than 8GB for comfortable local use. Check the VRAM table above for the exact resolution and precision trade-off.
Stable Diffusion 3.5 Medium 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.
Yes, the RTX 4090 (24 GB VRAM) can run Stable Diffusion 3.5 Medium comfortably at FP16. Expected generation time is around ~7s per image at 1024×1024.
Yes, Stable Diffusion 3.5 Medium has 1 ControlNet adapter available: Canny Edge. Each ControlNet adds roughly 1.5 GB of extra VRAM.
Very few LoRAs available for SD 3.5 Medium. The LoRA ecosystem for Stable Diffusion 3.5 Medium is rated as "minimal". Each LoRA adds roughly 0.1 GB of extra VRAM.
On a reference GPU (RTX 4090 24GB), Stable Diffusion 3.5 Medium generates a 1024×1024 image in approximately ~7s at FP16 with 28 inference steps. Faster GPUs with higher memory bandwidth will produce images more quickly.
See also