Sd

Stable Diffusion WebUI Forge install guide

A faster, low-VRAM Stable Diffusion WebUI — SD 1.5, SDXL, FLUX.
● Medium⏱ 30–45 min🐍 Python optional⬇ ~1.9 GBFree · open source⏳ Last verified: Pending test🔒 Official sources only🧩 Skills 7
PLAYING
0:00
Video coming soon · subscribe for updatesGet updates

Install in 1 clickOFFICIAL FILES · NO REPACK · NO SIGNUP

🔒 Verified source: github.com/lllyasviel⏳ Pending test
🧩 Teach this AI new skills

Unlock 5 new powers for Stable Diffusion

7 skills, mapped to what Stable Diffusion can do after you install them · tap a power

🔍
Power unlocked

Stable Diffusion can fix faces & upscale big

3 skills give this power
Tiled Diffusion & VAE (MultiDiffusion)🟠 Community

Stable Diffusion can make huge images on low VRAM

🔍🪶pkuliyi2015 · ★ 5k
ADetailer🟠 Community

Stable Diffusion can auto-detect and fix faces and hands

🔍Bing-su · ★ 4.8k
Ultimate SD Upscale🟠 Community

Stable Diffusion can upscale images in tiles

🔍Coyote-A · ★ 1.8k
🧬
Power unlocked

Stable Diffusion can learn new styles & models

2 skills give this power
Civitai helper extension🔵 Vendor-official

Stable Diffusion can browse and download Civitai models and LoRAs from its own UI

🧬civitai · ★ 2.4k
LoRAs / checkpoints (Civitai, Hugging Face)🟠 Community

Stable Diffusion can learn new styles and characters from added model files

🧬civitai.com
🪶
Power unlocked

Stable Diffusion can run on smaller GPUs

2 skills give this power
Forge (built-in ControlNet etc.)🟢 Official

Stable Diffusion runs as a faster A1111 fork with built-in ControlNet, and many A1111 extensions work

🪶🎛️lllyasviel · ★ 13.1k
Tiled Diffusion & VAE (MultiDiffusion)🟠 Community

Stable Diffusion can make huge images on low VRAM

🔍🪶pkuliyi2015 · ★ 5k
🎨
Power unlocked

Stable Diffusion can make images, media & voice

1 skill gives this power
Tag autocomplete🟠 Community

Stable Diffusion autocompletes booru tags while you type prompts

🎨DominikDoom · ★ 2.8k
🎛️
Power unlocked

Stable Diffusion can follow poses, depth & edges

1 skill gives this power
Forge (built-in ControlNet etc.)🟢 Official

Stable Diffusion runs as a faster A1111 fork with built-in ControlNet, and many A1111 extensions work

🪶🎛️lllyasviel · ★ 13.1k
Filters, safety notes & votes → full skills list

Step-by-step

0 / 0
  1. Pre-check: open Task Manager → Performance to see RAM and GPU. Then run this in Command Prompt to see GPU name, driver version and VRAM. Also check free disk space.
    nvidia-smi
    Do you see your GPU name and "Driver Version"?
  2. Download the one-click package (CUDA 12.1 + PyTorch 2.3.1, ~1.9 GB) from GitHub and extract with 7-Zip.
    Forge one-click package (GitHub) ↗
    See update.bat and run.bat?
  3. Run update.bat first (important — fixes old bugs), then run.bat.
    WebUI opened in the browser (http://127.0.0.1:7860)?
  4. You need a model: put an official SD 1.5 or SDXL .safetensors from Hugging Face into webui\models\Stable-diffusion. Start with SD 1.5 on 4 GB VRAM.
    SD 1.5 (Hugging Face) ↗
    Model shows in the Checkpoint list and an image generated?

Sizes are approximate and can change on the official page.

Errors & fixes

"Torch is not able to use GPU"

Update the NVIDIA driver; this package does not work on AMD/Intel GPUs.

No checkpoint / "No model found"

Put a .safetensors model in models\Stable-diffusion and press 🔄 refresh.

"CUDA out of memory" / "torch.cuda.OutOfMemoryError"

Your GPU ran out of VRAM. Pick a smaller model or image size and close other apps.

"No space left on device" / "not enough disk space"

Disk is full. Models are large — keep the free space listed above; clear old downloads and the Recycle Bin.

Your error isn't listed?

Official links

We never host or repack files. Always check the address bar shows the domain above.

Teach Stable Diffusion WebUI Forge new skills 7 skills

Forge: same extension system as A1111; ControlNet and many optimizations built in. Repo last pushed Jul 2025.

Where: Extensions tab

ExtensionsModels

🛡 Stay safe

Read first
  1. Official first — from the AI maker or the service’s own GitHub org / domain.
  2. Read SKILL.md and any scripts before installing. Skills can run code with your permissions.
  3. Never paste base64 or “curl … | sh” download-and-run lines from a skill.

Scan installed skills (free scanner by Snyk):

uvx snyk-agent-scan@latest <skills-folder>

Real incidents: ClawHavoc (341+ malicious skills) · Snyk ToxicSkills (76 / 3,984) · fake postmark-mcp

Forge (built-in ControlNet etc.)

🟢 Official

Faster A1111 fork; many A1111 extensions work.

Extensions★ 13.1kAGPL-3.0updated 1.3 yr ago⚠ Stale — no update in 1 yr+
  1. Extensions → Install from URL

⚠️ Not every A1111 extension is compatible; repo activity slowed (last push Jul 2025).

Can run codeReads your files
Official source ↗ github.com⏳ Pending test Did it work?

Civitai helper extension

🔵 Vendor-official

Browse/download Civitai models & LoRAs from the UI.

Extensions★ 2.4kMITupdated 2.3 yr ago⚠ Stale — no update in 1 yr+
  1. Install from URL

⚠️ Official Civitai, but last push Jul 2024.

Can run code
Official source ↗ github.com⏳ Pending test Did it work?

Tiled Diffusion & VAE (MultiDiffusion)

🟠 Community

Huge images on low VRAM.

Extensions★ 5kLicense: see repoupdated 2.3 yr ago⚠ Stale — no update in 1 yr+
  1. Install from URL

⚠️ Older (2024); custom license — check repo.

Can run codeReads your files
Official source ↗ github.com⏳ Pending test Did it work?

ADetailer

🟠 Community

Auto-detect and fix faces/hands.

Extensions★ 4.8kAGPL-3.0updated 2 days ago
  1. Extensions → Install from URL → https://github.com/Bing-su/adetailer

⚠️ Depends on ultralytics — avoid versions 8.3.41/8.3.42 (compromised).

Can run code
Official source ↗ github.com⏳ Pending test Did it work?

Tag autocomplete

🟠 Community

Booru-tag autocomplete in prompts.

Extensions★ 2.8kMITupdated 5 months ago
  1. Extensions → Available → search 'tag autocomplete'

⚠️ Low risk (UI only).

Can run code
Official source ↗ github.com⏳ Pending test Did it work?

Ultimate SD Upscale

🟠 Community

Tiled upscaling.

Extensions★ 1.8kGPL-3.0updated 2.4 yr ago⚠ Stale — no update in 1 yr+
  1. Install from URL

⚠️ Older (2024) but stable.

Can run code
Official source ↗ github.com⏳ Pending test Did it work?

LoRAs / checkpoints (Civitai, Hugging Face)

🟠 Community

Teach new styles/characters by adding model files.

Models
  1. Download .safetensors only
  2. Put LoRA in models/Lora, checkpoint in models/Stable-diffusion
  3. Prompt: <lora:filename:0.8>

⚠️ Avoid .ckpt/.pt/.bin pickles from unknown uploaders — they can execute code. Respect each model's license.

Can run codeReads your files
Official source ↗ civitai.com⏳ Pending test Did it work?

Stars, license and last update come from GitHub (17 Nov 2026). Commands are copied from official docs and are not tested on a real machine yet. Access tags are our summary — always check the source. Skills for every AI →

Next guides

Alternatives All Image →

Get new free AI tools by email

Optional · one short email when this video or a new free guide lands. No spam, one-click unsubscribe.