SD WebUI Forge

Deploy Stable Diffusion WebUI Forge with optimized VRAM management and FLUX support on Clore.ai GPUs

SD WebUI Forge is an optimized fork of the classic AUTOMATIC1111 Stable Diffusion WebUI, developed by the lllyasviel team. It delivers significantly better VRAM management (enabling SDXL on 4 GB GPUs), native FLUX model support, faster generation speeds, and full backward compatibility with all A1111 extensions and models. CLORE.AI's flexible GPU marketplace lets you pick the perfect GPU for Forge — from budget cards to top-tier A100s.

All examples can be run on GPU servers rented through CLORE.AI Marketplace.

Server Requirements

Parameter

Minimum

Recommended

RAM

8 GB

16 GB+

VRAM

4 GB

12 GB+

Disk

30 GB

200 GB+

GPU

NVIDIA GTX 1650 4GB+

RTX 3090, RTX 4090

Forge's key advantage is its VRAM optimizer: it can run SDXL on as little as 4 GB VRAM (with slower speed). For FLUX models, 12 GB VRAM is the practical minimum, with 24 GB for full quality and speed.

Quick Deploy on CLORE.AI

Docker Image: nykk3/stable-diffusion-webui-forge:latest

Ports: 22/tcp, 7860/http

Environment Variables:

Variable

Example

Description

CLI_ARGS

--xformers --medvram

Extra CLI arguments

COMMANDLINE_ARGS

--api --listen

Alternative CLI args env

Step-by-Step Setup

1. Rent a GPU Server on CLORE.AI

Head to CLORE.AI Marketplace:

Budget SD1.5: GTX 1660/2060 (6 GB) — plenty for 512/768px
SDXL capable: RTX 3080/3090 (10–24 GB)
FLUX capable: RTX 4090/A6000 (24+ GB)
Maximum quality: A100 80GB for batch generation

2. SSH into Your Server

ssh -p <PORT> root@<SERVER_IP>

3. Create Storage Directories

mkdir -p /root/sd-forge/{models,outputs,extensions,configs}
mkdir -p /root/sd-forge/models/{Stable-diffusion,VAE,Lora,ControlNet,embeddings,ESRGAN}

4. Pull and Run SD WebUI Forge

Standard launch:

docker run -d \
  --name sd-forge \
  --gpus all \
  -p 7860:7860 \
  -v /root/sd-forge/models:/app/stable-diffusion-webui/models \
  -v /root/sd-forge/outputs:/app/stable-diffusion-webui/outputs \
  -v /root/sd-forge/extensions:/app/stable-diffusion-webui/extensions \
  nykk3/stable-diffusion-webui-forge:latest

With API enabled and extra performance flags:

docker run -d \
  --name sd-forge \
  --gpus all \
  -p 7860:7860 \
  -v /root/sd-forge/models:/app/stable-diffusion-webui/models \
  -v /root/sd-forge/outputs:/app/stable-diffusion-webui/outputs \
  -v /root/sd-forge/extensions:/app/stable-diffusion-webui/extensions \
  -e CLI_ARGS="--api --xformers --enable-insecure-extension-access" \
  nykk3/stable-diffusion-webui-forge:latest

Low VRAM mode (4-6 GB GPUs):

docker run -d \
  --name sd-forge \
  --gpus all \
  -p 7860:7860 \
  -v /root/sd-forge/models:/app/stable-diffusion-webui/models \
  -v /root/sd-forge/outputs:/app/stable-diffusion-webui/outputs \
  -e CLI_ARGS="--api --medvram-sdxl --opt-sdp-attention" \
  nykk3/stable-diffusion-webui-forge:latest

Maximum performance (24+ GB VRAM):

docker run -d \
  --name sd-forge \
  --gpus all \
  -p 7860:7860 \
  -v /root/sd-forge/models:/app/stable-diffusion-webui/models \
  -v /root/sd-forge/outputs:/app/stable-diffusion-webui/outputs \
  -e CLI_ARGS="--api --xformers --no-half-vae" \
  nykk3/stable-diffusion-webui-forge:latest

5. Monitor Startup

docker logs -f sd-forge

Look for:

Running on local URL:  http://0.0.0.0:7860

Startup typically takes 2–5 minutes on first run.

6. Access the Web Interface

Your CLORE.AI http_pub URL for port 7860:

https://<order-id>-7860.clore.ai/

7. Add Models

Method 1: Download via CivitAI in the web UI

Go to Extensions → Installed → Models (some versions)
Or use the URL downloader in Settings

Method 2: Download directly on server

# Download SDXL base model
cd /root/sd-forge/models/Stable-diffusion
wget -O "sd_xl_base_1.0.safetensors" \
  "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors"

# Download FLUX.1-schnell (fast FLUX model)
wget -O "flux1-schnell.safetensors" \
  "https://huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/flux1-schnell.safetensors"

Method 3: HuggingFace CLI

docker exec -it sd-forge bash -c "
pip install huggingface_hub
huggingface-cli download stabilityai/stable-diffusion-xl-base-1.0 \
  sd_xl_base_1.0.safetensors \
  --local-dir /app/stable-diffusion-webui/models/Stable-diffusion/
"

Usage Examples

Example 1: Text to Image via Web UI

Open the Forge UI at your CLORE.AI URL
Select your model from the Checkpoint dropdown
Enter prompt: "cinematic portrait of a warrior, golden hour, 8k photography"
Set negative prompt: "blurry, low resolution, watermark, ugly"
Set width/height: 1024x1024 for SDXL, 512x768 for SD1.5
Set steps: 20–30, CFG: 7
Click Generate

Example 2: FLUX Generation

FLUX models work differently — no negative prompt, higher quality:

Select FLUX checkpoint (flux1-dev.safetensors)
Under Forge, select appropriate Unet and VAE if separate files

Enter prompt (no negative prompt needed):

A breathtaking landscape at sunset, mountains reflected in a pristine lake,
photorealistic, ultra detailed, professional photography

Steps: 20, CFG: 1.0 (FLUX uses lower CFG)
Sampler: Euler or DPM++ 2M

Example 3: ControlNet-Guided Generation

Install ControlNet extension (if not pre-installed):
- Go to Extensions → Available → Load from
- Search "ControlNet" and install
Download ControlNet models to /root/sd-forge/models/ControlNet/
In txt2img, expand ControlNet section
Upload reference image (pose, depth, canny edge)
Select preprocessor and model matching your reference type
Generate — output follows the reference structure

Example 4: API Usage

With --api flag, Forge exposes a REST API:

import requests
import base64
import io
from PIL import Image

BASE_URL = "http://localhost:7860"  # or CLORE.AI http_pub URL

# Text to Image
payload = {
    "prompt": "a serene Japanese garden with cherry blossoms, watercolor style",
    "negative_prompt": "ugly, blurry, low quality",
    "steps": 25,
    "cfg_scale": 7,
    "width": 1024,
    "height": 1024,
    "sampler_name": "DPM++ 2M",
    "batch_size": 1,
}

response = requests.post(f"{BASE_URL}/sdapi/v1/txt2img", json=payload)
result = response.json()

# Save the image
for i, img_b64 in enumerate(result["images"]):
    img_data = base64.b64decode(img_b64)
    img = Image.open(io.BytesIO(img_data))
    img.save(f"output_{i}.png")
    print(f"Saved output_{i}.png")

Example 5: Batch Generation Script

import requests
import base64
import io
from PIL import Image
import os

BASE_URL = "http://localhost:7860"

prompts = [
    ("cyberpunk city at night, neon lights, rain", "cyberpunk"),
    ("ancient forest, mystical fog, fantasy art", "fantasy"),
    ("minimalist logo design, geometric shapes, white background", "logo"),
    ("portrait of an elderly sailor, weathered face, oil painting", "portrait"),
]

os.makedirs("batch_output", exist_ok=True)

for prompt_text, filename in prompts:
    print(f"Generating: {filename}...")
    response = requests.post(
        f"{BASE_URL}/sdapi/v1/txt2img",
        json={
            "prompt": prompt_text,
            "negative_prompt": "low quality, blurry, watermark",
            "steps": 25,
            "cfg_scale": 7,
            "width": 1024,
            "height": 1024,
        },
    )
    
    if response.status_code == 200:
        img_b64 = response.json()["images"][0]
        img = Image.open(io.BytesIO(base64.b64decode(img_b64)))
        img.save(f"batch_output/{filename}.png")
        print(f"  Saved batch_output/{filename}.png")
    else:
        print(f"  Error: {response.status_code}")

Configuration

Key CLI Arguments

Argument

Description

--api

Enable REST API

--listen

Listen on all interfaces (required for CLORE.AI)

--port 7860

Change port

--xformers

Enable xFormers attention (faster, less VRAM)

--medvram

Medium VRAM mode (SD1.5 on 6GB)

--medvram-sdxl

Medium VRAM for SDXL (SDXL on 8GB)

--lowvram

Low VRAM mode (very slow, any GPU)

--no-half

Use float32 (more VRAM, more stable)

--no-half-vae

Keep VAE in float32 (prevents black images)

--opt-sdp-attention

PyTorch scaled dot product attention

--enable-insecure-extension-access

Allow extension installation

--skip-version-check

Skip Python/torch version checks

Forge-Specific Settings

Forge adds a Forge panel in the UI with:

Forge Unet: Select optimization backend (default, bnb, etc.)
Diffusers Torch Compilation: Enable for 20-30% faster generation (first run compiles)
GPU Weights: How much to keep on GPU vs CPU

Performance Tips

1. Use xFormers for 20-30% Less VRAM

--xformers

Automatically improves performance on most GPUs.

2. Forge's VRAM Optimizer

Forge automatically manages VRAM better than A1111. Just use the --medvram-sdxl flag for SDXL on 8-12 GB GPUs and let it handle the rest.

3. Enable Torch Compilation (Ampere+)

In the Forge tab in the UI, enable Diffusers Torch Compilation. First generation takes 2-3 minutes to compile, but subsequent ones are 20-30% faster.

4. Optimal Steps/Sampler Combos

Goal

Sampler

Steps

CFG

Speed

DPM++ SDE Karras

15-20

Quality

DPM++ 2M Karras

25-35

Artistic

Euler a

20-30

5-7

FLUX

Euler

5. Use Tile VAE for 2K+ Resolutions

For ultra-high resolution (2048×2048+), enable Tiled VAE in the SD tab to prevent VAE OOM errors.

6. Batch Locally with API

Instead of generating one at a time in the UI, use the API with batch_size for faster throughput:

payload = {
    "prompt": "...",
    "batch_size": 4,  # Generate 4 images at once
    "n_iter": 2,      # Run 2 iterations = 8 total images
}

Troubleshooting

Problem: Black or green images

VAE precision issue. Add flag:

--no-half-vae

Or use the sdxl-vae-fp16-fix.safetensors VAE.

Problem: "CUDA out of memory"

Try in order:

--medvram-sdxl (for SDXL)
--medvram (for SD1.5)
Reduce image resolution
--lowvram (last resort, very slow)

Problem: Extensions not loading

# Allow extension access
-e CLI_ARGS="--enable-insecure-extension-access"

Then install from Extensions tab in the UI.

Problem: Startup takes too long

Normal on first run — PyTorch and model hashes are computed. Subsequent starts are faster.

docker logs -f sd-forge  # Watch progress

Problem: Can't access UI from browser

Ensure the Forge process binds to 0.0.0.0:

Add --listen to CLI_ARGS
Verify port 7860 is in your CLORE.AI order port list

After placing .safetensors files in the correct folder, click 🔄 Refresh next to the Checkpoint dropdown.

Clore.ai GPU Recommendations

Use Case

Recommended GPU

Est. Cost on Clore.ai

Development/Testing

RTX 3090 (24GB)

~$0.12/gpu/hr

Production

RTX 4090 (24GB)

~$0.70/gpu/hr

Large Scale

A100 80GB

~$1.20/gpu/hr

💡 All examples in this guide can be deployed on Clore.ai GPU servers. Browse available GPUs and rent by the hour — no commitments, full root access.

PreviousInvokeAI NextOverview

Last updated 1 day ago

Was this helpful?

hashtagServer Requirements

hashtagQuick Deploy on CLORE.AI

hashtagStep-by-Step Setup

hashtag1. Rent a GPU Server on CLORE.AI

hashtag2. SSH into Your Server

hashtag3. Create Storage Directories

hashtag4. Pull and Run SD WebUI Forge

hashtag5. Monitor Startup

hashtag6. Access the Web Interface

hashtag7. Add Models

hashtagUsage Examples

hashtagExample 1: Text to Image via Web UI

hashtagExample 2: FLUX Generation

hashtagExample 3: ControlNet-Guided Generation

hashtagExample 4: API Usage

hashtagExample 5: Batch Generation Script

hashtagConfiguration

hashtagKey CLI Arguments

hashtagForge-Specific Settings

hashtagPerformance Tips

hashtag1. Use xFormers for 20-30% Less VRAM

hashtag2. Forge's VRAM Optimizer

hashtag3. Enable Torch Compilation (Ampere+)

hashtag4. Optimal Steps/Sampler Combos

hashtag5. Use Tile VAE for 2K+ Resolutions

hashtag6. Batch Locally with API

hashtagTroubleshooting

hashtagProblem: Black or green images

hashtagProblem: "CUDA out of memory"

hashtagProblem: Extensions not loading

hashtagProblem: Startup takes too long

hashtagProblem: Can't access UI from browser

hashtagProblem: Model not showing in dropdown

hashtagLinks

hashtagClore.ai GPU Recommendations

Server Requirements

Quick Deploy on CLORE.AI

Step-by-Step Setup

1. Rent a GPU Server on CLORE.AI

2. SSH into Your Server

3. Create Storage Directories

4. Pull and Run SD WebUI Forge

5. Monitor Startup

6. Access the Web Interface

7. Add Models

Usage Examples

Example 1: Text to Image via Web UI

Example 2: FLUX Generation

Example 3: ControlNet-Guided Generation

Example 4: API Usage

Example 5: Batch Generation Script

Configuration

Key CLI Arguments

Forge-Specific Settings

Performance Tips

1. Use xFormers for 20-30% Less VRAM

2. Forge's VRAM Optimizer

3. Enable Torch Compilation (Ampere+)

4. Optimal Steps/Sampler Combos

5. Use Tile VAE for 2K+ Resolutions

6. Batch Locally with API

Troubleshooting

Problem: Black or green images

Problem: "CUDA out of memory"

Problem: Extensions not loading

Problem: Startup takes too long

Problem: Can't access UI from browser

Problem: Model not showing in dropdown

Links

Clore.ai GPU Recommendations