Stable Diffusion v1.5 Archive

Stable Diffusion v1.5 Archive

Archived Stable Diffusion v1.5 checkpoints for ComfyUI that turn a text prompt into an image, kept for legacy testing. Includes the original file and an FP16 copy.

Made by Comfy-Org on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: This repository re-uploads Stable Diffusion v1.5 as an archive and packs the files for ComfyUI, a node-based tool that turns text prompts into images. It exists because RunwayML took down the original page. The card says the model is several generations behind and is kept for technical and accessibility reasons, such as testing legacy models.

Who it suits: It suits ComfyUI users who need the old v1.5 checkpoint, for example to test legacy workflows or to compare it with newer models.

Industry | Who uses it | How they use it | Example
Software development | Developers who test image pipelines | Run an old model to check that a workflow still works | A legacy workflow is tested against the v1.5 checkpoint
Research | Researchers who compare models | Use v1.5 as a baseline against newer generators | The same prompt is run on old and new models
Design and art | Digital artists | Generate images from text prompts with the classic model | A written description becomes a picture

You can skip it if you want a current image model, since the card itself calls this one several generations behind.

Where to use it:

• ComfyUI, on Windows, macOS or Linux
• The checkpoints folder under ComfyUI/models
• Python with the Hugging Face tools, to download the files

Use case | Who | What they get back
Legacy model testing | Developers | The original v1.5 checkpoint to test against
Smaller file | Users with limited memory | An FP16 copy of the same model
Baseline comparison | Researchers | An older model to measure newer ones against

How to set it up: You need ComfyUI and a place for the checkpoint files.

• A working ComfyUI install
• Python with the huggingface_hub package
• Disk space for the checkpoints you keep

1. Install the Hugging Face tools with Python.
2. Download the repository files with the second command below.
3. Place the checkpoints you want in the checkpoints folder under ComfyUI/models.
4. Pick a checkpoint in a ComfyUI text-to-image workflow.

pip install -U huggingface_hub
hf download Comfy-Org/stable-diffusion-1.5

Title: The three checkpoint files, all for the checkpoints folder
File | What the card says
v1-5-pruned-emaonly.safetensors | The original model, matching the RunwayML upload by hash
v1-5-pruned-emaonly-fp16.safetensors | The same model saved in FP16 and given a metadata header
interiordesignsuperm_v2.safetensors | Listed in the folder layout but not described

How to use it: The card gives no command and lists no workflow. After placing a checkpoint, select it in the checkpoint loader of a ComfyUI text-to-image workflow, type a prompt and run it.

Tool | What it does
checkpoints folder | Where ComfyUI looks for these files
Hugging Face download command | Fetches every file in the repository

Example: You place the FP16 file in the checkpoints folder, select it in a text-to-image workflow, and type a short description of a scene. ComfyUI returns an image generated from that text.

For newcomers and experts: Think of it as a classic image generator preserved for testing. A first small try is to place the FP16 file, select it in a basic text-to-image workflow and run a short prompt.

Two of the files are the same model. One matches the original RunwayML upload by hash, and the other is its FP16 conversion with a metadata header added. The trade-off of FP16 is lower precision for a smaller file. A third checkpoint appears in the folder listing, and the card does not explain it.

Download the repository files
Place a checkpoint in ComfyUI/models/checkpoints
Select it in a text-to-image workflow
Run the workflow
Get a generated image

Good to know:

• Archive: it is a preserved copy, and the original page was taken down by RunwayML
• Dated model: the card says it is several major generations behind
• Original versus FP16: the original is untouched, and the FP16 file has a metadata header added
• Third file: interiordesignsuperm_v2 is listed but not described, so check it before relying on it
• License: CreativeML OpenRAIL-M, so read its use terms before you generate images
• Cost to run: none named
• Data it reaches: the files you download and the prompts you run in ComfyUI
• Not for: use outside ComfyUI, or work that needs a current model

On Hugging Face, 13 November 2026

• Library: diffusion-single-file
• Downloads in the last 30 days: 590,374
• Likes: 205
• License: creativeml-openrail-m
• Languages: en
• Based on: runwayml/stable-diffusion-v1-5
• Tags: diffusion-single-file, comfyui

Links

• Model: https://huggingface.co/Comfy-Org/stable-diffusion-1.5
• Files: https://huggingface.co/Comfy-Org/stable-diffusion-1.5/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download Comfy-Org/stable-diffusion-1.5

Then follow the usage in its model card. Nothing in this kit runs by itself.