Stable Diffusion WebUI Forge - Neo

^{[ Neo | Classic ]}

Stable Diffusion WebUI Forge is a platform on top of the original Stable Diffusion WebUI by AUTOMATIC1111, to make development easier, optimize resource management, speed up inference, and study experimental features.
The name "Forge" is inspired by "Minecraft Forge". This project aims to become the Forge of Stable Diffusion WebUI.

- lllyasviel
^{(paraphrased)}

"Neo" mainly serves as an continuation for the "latest" version of Forge, which was built on Gradio 4.40.0 before lllyasviel became too busy... Additionally, this fork is focused on optimization and usability, with the main goal of being able to run the latest popular models via an easy-to-use GUI.

Tip

How to Install

Features [Oct.]

Most base features of the original Automatic1111 Webui should still function

New Features

Support Ideogram 4.0
- use Ideogram 4 Studio (see below) instead of the plain prompt box
- requires two accompanying modules (selected in the VAE / Text Encoder dropdowns):
  - the Flux2-family VAE (the same flux2-vae file used by FLUX.2 / Klein models)
  - an abliterated Qwen3-VL text encoder (auto-downloaded from SizorCloud/ideogram4-text-encoder-abliterated-merged if none is selected)
- pick the Ideogram4 preset in Settings/Presets (Euler / Simple / 20 steps / CFG 7)

Important

Ideogram 4 works best through its Studio, not as a plain prompt. The model was trained on structured JSON captions (description + regions + style). The built-in Ideogram 4 Studio builds this format for you: a canvas where you draw regions (objects / text), describe the background and pick style fields. A plain text prompt is still accepted (it is wrapped into a minimal valid caption automatically), but expect noticeably weaker results and more refusals without the Studio.

Note

Ideogram 4 Studio needs a second half: the unconditional model. The official pipeline pairs the main checkpoint with an unconditional counterpart used for the negative branch. Two options are available in the Studio panel:

Unconditional LoRA (default): the engine fetches ideogram4_unconditional.safetensors into models/Lora/ automatically; nothing to do.
Full unconditional checkpoint (recommended, matches the official design): download the official Ideogram-4-unconditional release and place it in the same folder as the main checkpoint — the Studio finds it automatically by the unconditional part of the file name. With no unconditional file present the Studio shows a download hint and the LoRA path stays active.

Support AuraFlow and Pony v7 (AuraFlow variant)
- pick the AuraFlow preset in Settings/Presets (Euler / FlowMatchEulerDiscrete / 30 steps / CFG 3.5 / Shift 1.73)
- AuraFlow is not guidance-distilled: keep CFG ≈ 3.5 (CFG 1.0 silently disables guidance)
- community Pony v7 checkpoints store the small text encoder (pile-T5) and VAE as separate files — select them in the Text Encoder / VAE dropdowns when they are not embedded in the checkpoint
- works with fp8_scaled and GGUF re-quantized releases

Tip

Practical notes for Ideogram 4 / AuraFlow / Pony v7

Select the matching Preset once in Settings/Presets — every parameter field (sampler, scheduler, steps, CFG, Shift) then fills with the values the model's authors recommend; per-model overrides are saved per preset like any other checkpoint selection.
Ideogram 4 is a large 13B model: generation is several times slower than AuraFlow (~2B) at the same resolution, and on a 24 GB card the text encoder is swapped out of VRAM between prompt encoding and sampling — the first generation after a model load takes an extra minute while the models shuffle. This is normal; repeated generations are fast.
Like the other large models here, these benefit from the speed flags (--cuda-malloc --cuda-stream --pin-shared-memory) and from keeping LoRA patching baked (not on-the-fly) when LoRAs are used.
Pony v7 image style follows the AuraFlow conventions (its fine-tune); use higher resolutions (1024+), which the Pony author also recommends.

Support Qwen-Image-2.1
Support Krea 2
Support Krea 2 Identity Edit
- require specific LoRA
Support Anima 2B / Anima 2.9B / Anima 3.8B
- automatically map LoRA / Controllllite for 2.9B & 3.8B
- qwen35_4b adapter requires Extension
Support Anima Edit
- require specific LoRA
Support Flux.2-Klein
- 4B / 9B (not FLUX.2-Dev)

Note

To toggle between img2img and reference (edit) for Qwen-Image-2.1 / Krea 2 / Anima / Flux.2-Klein, refer to Settings/Stable Diffusion

Support Ernie-Image
Support PiD 1.5
- sdxl / qwen / flux1 / flux2 (not PixelDiT)
- use PiD Integrated to automatically upscale after generation
Support Z-Image
Support Wan 2.2
- 14B (not 5B)
- use Refiner to achieve High Noise / Low Noise switching

Important

To export a video, you need to have FFmpeg installed

Support Mugen
- display the Shift slider for xl preset in Settings/Presets/XL
Support advanced SDXL models

Note

v-prediction: state_dict must include "v_pred"
Zero Terminal SNR: state_dict must include "ztsnr"
Rectified Flow: the model must include "rectified" in its path (e.g. file name or folder name)

Support Qwen-Image / Qwen-Image-Edit

Note

To be detected as an Edit model, the model must include both "qwen" and "edit" in its path (e.g. file name or folder name)

Support Flux Kontext

Note

To be detected as a Kontext model, the model must include "kontext" in its path (e.g. file name or folder name)

Implement ImageStitch Integrated
- support multi-image inputs for Edit models
- support FirstLastFrameToVideo for Wan 2.2
Support Nunchaku (SVDQ) Models (Deprecated)
- flux-dev, flux-krea, flux-kontext, qwen-image, qwen-image-edit, z-image-turbo
- only Flux and Qwen support LoRA currently
- see Commandline
Support Lumina-Image-2.0
Support Chroma1-HD
Support MixedPrecision Models
- fp4mixed / fp8mixed / mxfp8 / nvfp4 / fp8_scaled / int8_convrot / convrot_w4a4 / asym_w4a8_int8 / w6a8_int8
Support Flux.2-Small-Decoder & Qwen2D VAE

Tip

Check out Download Models for where to get each model and the accompanying modules

Tip

Check out Inference References for how to use each model and the recommended parameters

Rewrite Preset System
- now save the checkpoint/module selection and parameters per each Preset

Note

This overrides the UI Defaults for the controlled parameters

This Fork (Ideogram 4 / AuraFlow maintenance)

Note

The items below are this fork's own additions on top of Neo; they are documented to keep the difference with upstream explicit. Bug-fix history is kept in Releases (each entry lists the upstream issue number it addresses).

Ideogram 4 Studio: colors and object management
- + next to the object palette opens the system color picker; a color is added only when the picker is confirmed (OK), not while browsing it
- ✕ in the object editor deletes the selected object (previously only possible from the canvas)
- the palette is limited to 5 colors per object (the model's limit) and duplicates are dropped on restore
Restore Stealth Infotext (opt-in; upstream Neo removed it)
- Settings → Infotext → "Stealth infotext mode": Alpha / RGB / None (default None = identical to upstream behavior)
- writes a gzip-compressed copy of the infotext into the least-significant bits of the image pixels; it survives re-encoding / copy-paste / re-upload that strip text metadata
- reading side (PNG Info, drag-and-drop, Read generation parameters) recovers infotext from the pixels automatically when the standard metadata is gone; images with real transparency keep their alpha values (each alpha changes by at most 1/255)
Prompt Group Pre-Encode built-in script
- appears as an accordion under Scripts in txt2img / img2img / inpaint; disabled by default
- pre-encodes the prompts of the upcoming batches in one pass while the text encoder is loaded, so batch generation (large models like Ideogram 4, where TE load costs minutes) encodes each prompt once instead of re-loading the TE per batch
- group size 2–32; stateful passes (Refiner, Hires pass, kontext/edit/reference engines, subseed variation) are skipped automatically; a failed pre-encode falls back to the normal per-batch encoding
Memory-management fixes
- a never-loaded / unloaded model entry no longer crashes cleanup_models() and poisons every later generation
- memory_required activation estimate aligned with the current reference for flash-attention paths, so int8 / convrot quantized checkpoints stay resident under Hires.fix instead of being force-offloaded (upstream issue #1537 scenario)

Removed Features

Optimizations

Note

Put every upscaler (.pth / .safetensors) inside the ESRGAN folder

Tip

Check out OpenModelDB for where to get upscalers

Note

If your GPU does not support the latest PyTorch, manually install older version of PyTorch

Update some packages to newer versions
Update recommended Python to 3.13.12
many more... ™️

Commandline

These flags can be added after the set COMMANDLINE_ARGS= line in the webui-user.bat (in the same line ; separate each flag with space)

Tip

Use python launch.py --help to see all available flags

--xformers: Install the xformers package to speed up generation

Warning

xformers does not support RTX 50s

--port: Specify a server port to use
- defaults to 7860
--api: Enable API access

by. Neo

--cuda-malloc: Improve memory allocation
--cuda-stream: Enable async weight offloading
--pin-shared-memory: Improve RAM utilization
--expandable-segments: Enable experimental PyTorch allocator (may prevent OutOfMemory errors on certain platforms)

--uv: Replace the python -m pip calls with uv pip to massively speed up package installation
- require uv to be installed first (see Extra Installations)
--uv-symlink: Same as above; but additionally pass --link-mode symlink to the commands
- significantly reduce installation size (~7 GB to ~100 MB)
--uv-local-cache: Same as above; but additionally set UV_CACHE_DIR to a .uv-cache folder within WebUI directory
- speed up installation on non-default drive (i.e. not C: on Windows)
- allow clean uninstallation by simply deleting the WebUI directory

Important

symlink means it will directly access the packages from the cache folder instead of copying the packages over ; refrain from clearing the cache when using this option

--model-ref: Points to a central models folder that contains all your models
- said folder should contain subfolders like Stable-diffusion, Lora, VAE, ESRGAN, etc.

Important

This simply replaces the models folder rather than adding on top of it

--forge-ref-a1111-home: Point to an Automatic1111 installation to load its models folders
- i.e. Stable-diffusion, text_encoder, etc.
--forge-ref-comfy-home: Point to a ComfyUI installation to load its models folders
- i.e. diffusion_models, clip, etc.
--forge-ref-comfy-yaml: Point to the ComfyUI extra_model_paths.yaml to load its configurations
- i.e. base_path, checkpoints, etc.

--sage: Install the sageattention package to speed up generation
- will also attempt to install triton automatically
--flash: Install the flash_attn package to speed up generation
--nunchaku: Install the nunchaku package to inference SVDQ models

Warning

Using nunchaku will fall back to older version of PyTorch

--onnxruntime-gpu: Install the onnxruntime with the latest GPU support

--fast-fp8: Use the torch._scaled_mm function when the model type is float8_e4m3fn
--fast-fp16: Enable the allow_fp16_accumulation option
--autotune: Enable the torch.backends.cudnn.benchmark option
- this is slower in my experience...
--tiled-conv2d: Replace Conv2d ops with tiled variants
- has greater reduction for SD1 and SDXL VAE; less for Wan VAE
- 64 / 128 / 256 / 512

--use-ck-attention: Use the Comfy-Kitchen attention to speed up generation
- override other attention packages
--enable-triton-backend: Enable the use of Triton backend in comfy-kitchen
- might speed up inference
--pynvml: Use the NVIDIA Management Library to determine the actual amount of free VRAM
- prevent system freeze when running other programs

Installation

Install git

Clone the Repo

git clone https://github.com/Haoming02/sd-webui-forge-classic sd-webui-forge-neo --branch neo

Setup Python

Recommended Method

Install uv

Set up venv

cd sd-webui-forge-neo
uv venv venv --python 3.13 --seed

Add the --uv flag to webui-user.bat

Deprecated Method

Install Python 3.13.12
- Remember to enable Add Python to PATH

(Optional) Configure Commandline
Launch the WebUI via webui-user.bat
During the first launch, it will automatically install all the requirements
Once the installation is finished, the WebUI will start in a browser automatically

Tip

For AMD, refer to CS1o 's Guide
For Linux and macOS, refer to Wiki
For Docker (Nvidia), refer to Docker

Tip

Check out Extra Installations for how to install git, uv, and FFmpeg

Attention Functions

Note

The --xformers, --flash, and --sage args are only responsible for installing the packages, not whether its respective attention is used (this also means you can remove them once the packages are successfully installed)

Caution

Do not just blindly install all of them
Nowadays the native PyTorch scaled_dot_product_attention is usually as fast, and also more stable

Forge Neo tries to import the packages and automatically choose the first available attention function in the following order:

SageAttention
FlashAttention
xformers
PyTorch
Basic

Tip

To skip a specific attention, add the respective disable arg such as --disable-sage

Issues & Requests

Issues about removed features will simply be ignored
Issues that is obviously user-error will simply be ignored
Issues regarding AMD GPU will simply be ignored
Issues running non-official models will simply be ignored
- do not just randomly download every single finetune/quant you find
Issues about 3rd-party Extensions will simply be ignored
- extension should support the UI, not the other way around
Issues caused by StabilityMatrix will simply be ignored
- only open an Issue if you can reproduce it on a clean install following the official Installation instruction

Caution

If you post NSFW images/videos, you will immediately be banned
- the sole discretion is on me ; if you are unsure, just generate cats and dogs...

Tip

Check out the Wiki & FAQ

Special thanks to AUTOMATIC1111, lllyasviel, and comfyanonymous, kijai, city96,
along with the rest of the contributors,
for their invaluable efforts in the open-source image generation community

_{Buy me a Coffee ☕~}
_{PayPal me 💳~}

Name		Name	Last commit message	Last commit date
.github		.github
backend		backend
docker		docker
extensions-builtin		extensions-builtin
extensions		extensions
html		html
javascript		javascript
localizations		localizations
models		models
modules		modules
modules_forge		modules_forge
scripts		scripts
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
download_configs.py		download_configs.py
launch.py		launch.py
pyproject.toml		pyproject.toml
requirements.txt		requirements.txt
script.js		script.js
style.css		style.css
webui-user.bat		webui-user.bat
webui-user.sh		webui-user.sh
webui.bat		webui.bat
webui.py		webui.py
webui.sh		webui.sh

Navigation Menu

Repository navigation

About

Repository files navigation

Stable Diffusion WebUI Forge - Neo

Features [Oct.]

New Features

This Fork (Ideogram 4 / AuraFlow maintenance)

Removed Features

Optimizations

Commandline

by. Neo

Installation

Attention Functions

Issues & Requests

About

Releases

Packages

Contributors

Languages

Latest commit

History

Folders and files

Repository files navigation

Stable Diffusion WebUI Forge - Neo

Features [Oct.]

New Features

This Fork (Ideogram 4 / AuraFlow maintenance)

Removed Features

Optimizations

Commandline

by. Neo

Installation

Attention Functions

Issues & Requests

About

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages