How much VRAM does Stable Diffusion 1.5 need?

Stable Diffusion 1.5 is an image generation model by Stability AI and others (0.86B; text encoder: CLIP ViT-L). Old but light, with a huge ecosystem of fine-tunes and LoRAs.

Change precision, resolution →

VRAM by precision and resolution

Bold = VRAM needed when ComfyUI swaps the text encoder and the model. "All in VRAM" = keeping both loaded. Text encoder assumed at FP8.

GPUs that run Stable Diffusion 1.5 (34 GPUs, 512×512)

ComfyUI also runs on AMD Radeon (ROCm) and Intel Arc, but setup is harder than on NVIDIA and some features (such as FP8 acceleration) are not supported.

License

• License: CreativeML OpenRAIL-M (commercial use: Allowed with conditions). Always read the full license before using outputs commercially.
• Download: Hugging Face (stable-diffusion-v1-5/stable-diffusion-v1-5). FP8 and GGUF builds (loaded with ComfyUI-GGUF) are widely shared.

Other image & video models

→ Image & Video AI VRAM Calculator (all 15 models) / Local LLM VRAM Calculator

Estimates for ComfyUI, about ±20%. Model specs from the publisher's config files and released file sizes (checked October 2026).