Qwen-Image 2.1 Turbo in Stable Forge UI Neo (8 GB VRAM) - One Click Installer
Qwen-Image 2.1 Turbo now runs inside Stable Diffusion Forge Neo — the official Turbo model, real image edits and edits with more than one reference image, all from a simple web page instead of a node graph. In side-by-side tests against ComfyUI with the same models, prompts and seeds, the images came out practically the same.
This one-click Windows installer sets up Forge Neo 2.30, Python 3.13 and the Qwen models for you, and Neo opens with the Turbo settings already filled in: 8 steps, CFG 1, the sampler for clean text-to-image results and the one that keeps edits from burning.
Already have Forge Neo? The included update file moves you to the tested version, and the link file lets Neo use the models you already have from ComfyUI, Automatic1111 or older Forge — nothing is copied or moved.
Pick your setup at install: Recommended (Turbo int8 + w4a8 encoder, ~14 GB), Lowest RAM (GGUF Q5 for 16 GB system RAM), Full (int8 + int8 encoder for 32 GB+ RAM) or Skip to use your own models.
Runs on 8 GB VRAM — about 13 seconds per 1024×1024 image on 8 GB, ~11 seconds on 16 GB. Needs an NVIDIA GPU with driver 580 or newer (PyTorch 2.13 / CUDA 13), Windows 10/11 and ~30 GB free storage. Git, uv and Python are handled automatically.
What you get
A one-click Windows installer for ComfyUI Portable, both Qwen-Image 2.1 workflows — Text-to-Image and Image Edit (I2I) — and the custom nodes they need: ComfyUI Manager, ComfyUI-GGUF and rgthree.
The download menu — pick your VRAM tier:
Base model: FP8 (int8, ~7 GB, higher quality) into diffusion_models/, or GGUF Q5_K_M (~4–7 GB by quant, low VRAM) into unet/ Text encoder: qwen3vl_8b int8 (standard) or w4a8 (extra low VRAM) into text_encoders/ VAE: qwen_image_2.1_vae_bf16 into vae/ — downloads with any choice
Optional turbo LoRAs into loras/: none, Viggle 6-step, Alibaba-PAI 4-step, or both to compare. They cut editing to 4–6 steps at cfg 1. They're consistently great for image editing, but text-to-image on them is hit-or-miss — use turbo for edits, and the standard model at full steps for reliable text-to-image. The matching free turbo edit workflow runs them.
System requirements
OS: Windows 10 or 11, 64-bit.
GPU: NVIDIA RTX 30XX / 40XX / 50XX. FP8: 12 GB. On a 16 GB card a 1024×1024 image takes about 1–2 minutes at 25 steps. GGUF + w4a8: runs on 6–8 GB and still produces good quality.
Disk: at least 30 GB free.
Handled for you: Git, 7-Zip and the correct PyTorch build are installed automatically.
Getting started
1. Put the install .bat in its own dedicated folder and double-click. Use a simple local path like C:\Qwen\ — avoid Desktop, Documents, and cloud-synced folders.
2. At the menu, pick the base model and text encoder for your card: 8 GB → GGUF + w4a8; 12 GB+ → FP8 + int8 for best quality. Add a turbo LoRA if you'll mostly be editing.
3. Load either workflow (Text-to-Image or Edit) and confirm the models are selected.
4. Start around 25 steps at 1024×1024.
5. For fast edits, run a turbo LoRA with the free turbo edit workflow at 4–6 steps and cfg 1.
Troubleshooting
Install fails or behaves oddly: check the install path first. A cloud-synced folder (OneDrive, Dropbox) or a deep path with spaces is the most common cause. Move to C:\Qwen\ and re-run.
Out of memory: choose the GGUF base and the w4a8 text encoder at the download menu — that's the 6–8 GB tier.
Text-to-image comes out smeared or incomplete: check whether a turbo LoRA is active. They're reliable for editing but hit-or-miss for text-to-image — turn it off and run the standard model at full steps.
A model isn't showing in a loader: the FP8 base lives in diffusion_models/ and the GGUF base in unet/, and they're loaded by different loader nodes — select the one that matches what you downloaded.
Licence & credit
Qwen-Image 2.1 is by the Qwen team (Alibaba). ComfyUI support is by Comfy-Org, the GGUF quants by Abiray, and the turbo LoRAs by Viggle and Alibaba-PAI. This product is the installer and workflow packaging — it automates the setup of their work into a one-click process.
Licence note: Qwen-Image 2.1 is released under the Qwen Research License — non-commercial use only. Unlike the earlier Apache-licensed Qwen-Image release, commercial use requires a separate licence from Tongyi Lab (Alibaba). The GGUF quants and turbo LoRAs are derived from it and carry the same licence. Read the terms on the model's Hugging Face page before any commercial use.