Forge Neo UI> is an AI image and video generation app that offers a simpler experience than ComfyUI and flexibility not found on popular providers (think ChatGPT, Claude or Gemini).
As the newest version of Forge UI, Forge Neo UI expands model support, and improves integration with modern workflows. More importantly it brings life to the project, as it's actively maintained (Forge UI classic was last updated 11 months ago).
This guide covers what Forge Neo offers, who it is for, and how to get started on Thunder Compute with minimal setup.
Forge Neo: Supported Models
Forge Neo UI is designed to work with a broad range of models, making it a flexible. Below are the current supported models and their characteristics. Note that while most of them should run on standard GPUs, other require lots of VRAM.
| Model | Type | Architecture | Characteristics | Min VRAM | Recommended VRAM |
|---|---|---|---|---|---|
| SD 1.5 | Image | UNet Latent diffusion |
- Foundational model - Largest LoRA and extension ecosystem - Fast generation - Best at 512px |
4 GB | 6 GB |
| SDXL | Image | Dual UNet Latent diffusion |
- Higher resolution output (1024px native) - Improved prompt adherence - Larger than SD 1.5 |
8 GB | 10 GB |
| Lumina-Image-2.0 | Image | DiT (diffusion transformer) | - High aesthetic quality - Strong text rendering - Supports multilingual prompts - Research-grade outputs |
12 GB | 16 GB |
| FLUX Dev | Image | Flow matching transformer (12B) | - State-of-the-art photorealism - Excellent prompt adherenceSlower than Schnell - For non-commercial use |
16 GB | 24 GB |
| FLUX Kontext | Editing | Flow matching transformer (12B) | Reference-image-conditioned editing - Preserves subject identity across edits - Strong style transfer |
16 GB | 24 GB |
| Z-Image | Image | DiT Flow matching |
- Efficient high-resolution synthesis - Strong structural coherence - Optimized for commercial workflows |
12 GB | 16 GB |
| Z-Image Turbo | Image/span> | Distilled DiT | - Distilled variant of Z-Image - Significantly faster - Slight quality tradeoff |
10 GB | 12 GB |
| FLUX.1 Klein 4B | Image | Flow matching transformer (4B) | Lightweight FLUX variant - Faster and lower VRAM - Good quality-to-cost ratio |
8 GB | 12 GB |
| FLUX.1 Klein 9B | Image | Flow matching transformer (9B) | - Mid-tier FLUX variant - Closer to full FLUX quality - Better prompt fidelity than 4B |
12 GB | 16 GB |
| Ernie-Image | Image | DiT (Baidu) | - Strong Chinese-language prompt support - High aesthetic quality for Asian art styles - Multilingual |
12 GB | 16 GB |
| Wan 2.2 T2V | Video | Video DiT Text-to-video |
Text-to-video generation - Produces short clips (5s max) - Strong motion coherence |
16 GB | 24 GB |
| Wan 2.2 I2V | Video | Video DiT Image-to-video |
- Animates a still image - Preserves subject appearance - Natural motion from a single frame |
16 GB | 24 GB |
| Qwen-Image | Image | Multimodal transformer (Alibaba) | - Strong multilingual and Chinese prompt handling - High visual quality - Instruction-following generation |
16 GB | 24 GB |
| Qwen-Image-Edit | Editing | Multimodal transformer (Alibaba) | - Instruction-based image editing - Understands natural language edit commands - Preserves non-edited regions |
16 GB | 24 GB |
| Anima | Video | Video diffusion AnimateDiff |
- Animation and motion synthesis - Supports looping outputs - Strong for stylized and character animation |
12 GB | 16 GB |
LoRA, ControlNet, and IP-Adapter weights load natively without manual patching, and the model manager handles switching between checkpoints without restarting the server. This means you can move between photorealistic, anime, concept-art, and video workflows from a single interface.
Forge Neo: Use Cases
Forge Neo UI targets a wide spectrum of creative tasks.
<ul><li><strong>Iterating concepts</strong> by generating dozens of variations from a single prompt in batch mode.</li><li><strong>Inpainting and outpainting</strong> to extend or repair images at full resolution.</li><li><strong>Preparing print-quality assets</strong> with the included upscaling pipeline, which supports Real-ESRGAN and Tile Diffusion.</li><li><strong>Producing short looping clips</strong> or to animate still images.</li></ul>
On the more technical side it's also a great prototyping environment.
<ul><li><strong>Testing new LoRA</strong> training runs</li><li><strong>Benchmarking prompt engineering</strong> approaches.</li></ul>
Because the UI consolidates all these workflows, teams can use a single tool rather than juggle several applications.
A History of Stable Diffusion UIs
Stable Diffusion UIs have gone through several distinct generations, each solving problems the previous one left open. A great way to understand where Forge Neo fits is to take a brief look at the ecosystem it emerged from.
Automatic1111
Launched in 2022, AUTOMATIC1111 (often shortened to A1111) is the web-based user interface for Stable Diffusion that defined the standard for community-driven image generation tools when it.
It introduced the concept of a browser-accessible local server with an extensions marketplace, txt2img and img2img functionality, and a growing library of community scripts. For years it was the entry point to get into self-hosted diffusion models.
Its limitations became more apparent as models grew larger and more architecturally diverse. A1111 was built around SD 1.5, and adapting it to SDXL and later architectures required increasingly convoluted workarounds. Memory management was manual, performance was inconsistent across GPU generations, and the codebase became difficult to maintain.
Forge UI
Forge UI, developed by lllyasviel, was a direct response to A1111's performance ceiling. As the direct ancestor of Forge Neo they share a lot in terms of design philosophy.
It introduced a rewritten backend that applied GPU memory optimization, dramatically reducing VRAM requirements for large models. It could often run a workflow that required 24 GB of VRAM in 8 GB or less, supporting a much wider range of hardware.
Forge UI kept near-full compatibility with A1111 extensions, making it easy for existing users to migrate. Its architecture also made it easier to add support for new model families quickly, which is how it became one of the first UIs to ship reliable FLUX support.
ComfyUI
ComfyUI is fundamentally different to both A1111 and Forge. Rather than presenting a simple form UI, it exposes the diffusion pipeline as a node graph, where each processing step is a draggable node that can be wired to any other.
This modular approach gives users precise control over the generation process and makes it straightforward to build complex multi-model pipelines.
The tradeoff is a steeper learning curve. Casual users will find ComfyUI significantly more demanding than Forge-based alternatives. It excels for advanced workflows, custom pipeline research, and production environments where reproducibility and modularity matter more than ease of use.
Forge Neo UI
Forge Neo UI has a simplified interface, and support for video generation models. Memory management is further improved over the original Forge, and the extension API is more stable, making third-party integrations more reliable.
For a capable, well-supported, and actively maintained interface without the node-graph complexity of ComfyUI, Forge Neo represents the most complete current option.
Running Forge Neo on Thunder Compute Instances
Thunder Compute offers a Forge Neo instance template that provisions a GPU-backed environment with everything pre-installed.
Avoid setup and start working with Forge Neo in minutes. Thunder Compute instances give you access to high-end GPUs like the RTX A6000 at $0.35/hr, which means generation times are fast and large SDXL or FLUX models load without memory pressure.
For a broader overview of running Stable Diffusion in the cloud, see the Thunder Compute guide to running Stable Diffusion.
Setup
There easiest way to launch a Forge Neo instance by running a few commands in theCLI:
<ol><li>First, <a href="https://www.thundercompute.com/docs/cli/quickstart" rel="noopener" target="_blank">install tnr</a>.</li><li><code>tnr create --template forge-neo</code> and choose your instance specs.</li><li><code>tnr connect 0</code> where 0 is the instance ID.</li><li><code>start-forgeneo</code> which will output a link to access Forge Neo. It might take a minute or two to get started.</li></ol>
You can find download links for all supported model checkpoints, LoRAs, and supporting files in the Forge Neo model download index.
Final Thoughts on Forge Neo UI
Forge Neo UI is currently the strongest choice if you want a maintained, high-performance Stable Diffusion interface without the steep ramp of ComfyUI.
It handles the full range of modern model architectures, supports both image and video workflows, and has a growing extension ecosystem.
If you want to try Forge Neo without a lengthy local setup, launch a Thunder Compute instance from the Forge Neo template and start generating in minutes.