Model reference · open weights
stable-diffusion-3.5-large is an open-weight image model from Stability AI. stable-diffusion-3.5-large (BF16) weighs 43.9 GB; the smallest configuration that runs it is RTX 4090 24 GB.
What it is
| Released by | Stability AI |
|---|---|
| Released | 2024-10-22 |
| Parameters | 8.1B |
| VRAM | 43.9 GB for the weights |
What it runs on
| Card | One image | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 4060 Ti 16 GB | does not fit | |
| RTX 3090 24 GB | tight (encoders offloaded) | 23.4 GB |
| RTX 4090 24 GB | tight (encoders offloaded) | 23.4 GB |
| RTX 5090 32 GB | fits (encoders offloaded) | 31.0 GB |
| L40S 48 GB | fits (encoders offloaded) | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
How it works
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel, then Templates → SD3.5 Simple: it loads ComfyUI's own build of this model, the files above.
# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the files of the template “SD3.5 Simple” (13.9 GB)
get Comfy-Org/stable-diffusion-3.5-fp8 sd3.5_large_fp8_scaled.safetensors checkpoints
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST and PORT are your machine's, from its page in the console
ssh -L 8188:localhost:8188 dev@HOST -p PORT