Stable Cascade
Stableby Stability AI
Two-stage cascade pipeline from Stability AI using Wurstchen architecture. Stage C (~3.6B) generates in a very small latent space, then Stage B (~1.5B) decodes to full resolution. More VRAM-efficient than single-stage models of similar quality.
VRAM requirements, GPU fit, and setup notes for Stable Cascade, including 8GB/12GB fit guidance where relevant. Recommended runtimes: ComfyUI and Diffusers support. Best download size: ~14.4 GB at FP16.
- Two-stage cascade — more efficient VRAM usage
- Stage C operates in very small latent space
- Wurstchen architecture
Your hardware
Detecting...
Image Quality Benchmarks
Measured quality metrics for Stable Cascade outputs.
How often humans prefer this model's output (0-100%)
Visual quality and composition rating (5-9 scale)
VRAM Requirements by Resolution and Precision
Compare which GPUs can run Stable Cascade 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)
| Resolution | VRAM Required | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 | 15.3 GB | S● | D● | F● | A● |
| 768×768 | 15.6 GB | S● | D● | F● | A● |
| 1024×1024 | 16.0 GB | S● | D● | F● | B● |
Optimization Tips
Turbo / LCM distillation
Use distilled scheduler at 4-8 steps for faster iteration
ControlNets available
Add guided generation with 2 adapters (+1.5 GB VRAM each)
Run with Python
from diffusers import StableCascadeCombinedPipeline
import torch
pipe = StableCascadeCombinedPipeline.from_pretrained(
"stabilityai/stable-cascade",
torch_dtype=torch.float16
)
pipe.to("cuda")
image = pipe(
prompt="your prompt here",
num_inference_steps=20,
guidance_scale=4.0,
height=1024,
width=1024,
).images[0]
image.save("output.png")Get started
Setup instructions for running Stable Cascade locally
1. Download the model
Get the checkpoint from HuggingFace
2. Place in:
ComfyUI/models/checkpoints/3. Launch ComfyUI
python main.pyMemory Breakdown
VRAM allocation at 1024×1024 on RTX 4090 24GB (24 GB)
Estimated Generation Time
Time per image at 1024×1024, 28 steps, FP16.
Sample Outputs
Available Formats, Downloads & Setup
Download Stable Cascade in the precision that matches your GPU. Lower precision usually means less VRAM pressure, while higher precision keeps more quality.
| Format | Präzision | Größe | Anbieter | |
|---|---|---|---|---|
| safetensorsEmpfohlen | FP16 | 14.4 GB | official | Herunterladen |
ControlNet Support
2 ControlNets available for Stable Cascade. ControlNets add guided image generation (edges, depth, pose) at the cost of extra VRAM.
Canny Edge
+1.5 GB VRAMOfficial Stability AI canny ControlNet for Stable Cascade Stage C.
Inpainting
+1.5 GB VRAMOfficial Stability AI inpainting ControlNet for Stable Cascade Stage C.
LoRA Ecosystem
LimitedVery few LoRAs available. Stable Cascade was largely eclipsed by SD 3.x and Flux.
Related Workflows
You might also like
Frequently asked questions
FAQ — Stable Cascade VRAM, Runtimes & Fit
How much VRAM does Stable Cascade need?
Stable Cascade (3.6B parameters) requires approximately 16.0 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.
Can I run Stable Cascade on an 8GB GPU?
Stable Cascade usually needs more than 8GB for comfortable local use. Check the VRAM table above for the exact resolution and precision trade-off.
Does Stable Cascade work in ComfyUI and Diffusers?
Stable Cascade 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 Stable Cascade on RTX 4090?
Yes, the RTX 4090 (24 GB VRAM) can run Stable Cascade comfortably at FP16. Expected generation time is around ~10s per image at 1024×1024.
Does Stable Cascade support ControlNet?
Yes, Stable Cascade has 2 ControlNet adapters available: Canny Edge, Inpainting. Each ControlNet adds roughly 1.5 GB of extra VRAM.
Does Stable Cascade have LoRA support?
Very few LoRAs available. Stable Cascade was largely eclipsed by SD 3.x and Flux. The LoRA ecosystem for Stable Cascade is rated as "minimal". Each LoRA adds roughly 0.2 GB of extra VRAM.
How fast is Stable Cascade?
On a reference GPU (RTX 4090 24GB), Stable Cascade generates a 1024×1024 image in approximately ~10s at FP16 with 28 inference steps. Faster GPUs with higher memory bandwidth will produce images more quickly.
About Stable Cascade
See also