<h1 id="optimized-low-vram-multi-lora-workflow-for-flux.1-dev-(gguf)">Optimized Low-VRAM Multi-LoRA Workflow for Flux.1 Dev (GGUF)</h1>Another new, refined and enhanced workflow by Experimental_dAIverThis workflow delivers the full power of Flux.1 Dev in GGUF format, specially optimized for GPUs with less than 8 GB VRAM, like my RTX 4050 with only 6 GB. The integrated CacheDiT_Model_Optimizer and PatchSageAttentionKJ (both optional!) provide a noticeable speed boost with almost no quality loss. Full NdSuperLoraLoader support for easy multi-LoRA stacking with automatic trigger-word integration, the intuitive selectLatentSizePlus aspect-ratio and resolution selector, plus a complete SEEDVR2 Video Upscaler Subgraph (base provided by @LumaRift) for stunning high-resolution results complete this elegant and highly flexible setup.Version 1.5 is my first public release and brings significant improvements in speed, usability, multi-LoRA handling and upscaling quality — while remaining extremely VRAM-efficient (tested on RTX 4050 with only 6 GB).Key features in v1.5:<ul><li>NdSuperLoraLoader with full multi-LoRA support, auto-fetch trigger words and easy strength control</li><li>selectLatentSizePlus — intuitive aspect-ratio and resolution selector with beautiful presets (including golden-ratio-friendly options) plus easy orientation swap</li><li>Full SEEDVR2 Video Upscaler Subgraph — powerful DiT-based high-end upscaler that delivers stunning 4K+ results with intelligent resolution handling, Lab color correction and temporal settings. Works exceptionally well on still images too, producing superior detail and coherence</li><li>Improved workflow organization, expanded notes with recommended settings, and more robust saving options via SaveImageExtended</li><li>CacheDiT and SageAttention integration for optimized Flux performance on low-VRAM hardware</li></ul><hr /><h3 id="required-custom-nodes">Required Custom Nodes</h3><ul><li>ComfyUI-GGUF - <a target="_blank" rel="ugc" href="https://github.com/city96/ComfyUI-GGUF">https://github.com/city96/ComfyUI-GGUF</a> - UnetLoaderGGUF + CLIPLoaderGGUF</li><li>nd-super-nodes - <a target="_blank" rel="ugc" href="https://github.com/HenkDz/nd-super-nodes">https://github.com/HenkDz/nd-super-nodes</a> - NdSuperLoraLoader with tags, trigger words &amp; beautiful UI</li><li>save-image-extended-comfyui - <a target="_blank" rel="ugc" href="https://github.com/thedyze/save-image-extended-comfyui">https://github.com/thedyze/save-image-extended-comfyui</a> - Advanced saving with metadata &amp; dynamic filenames</li><li>ComfyUi-MzMaXaM - <a target="_blank" rel="ugc" href="https://github.com/MzMaXaM/ComfyUi-MzMaXaM">https://github.com/MzMaXaM/ComfyUi-MzMaXaM</a> - selectLatentSizePlus</li><li>ComfyUI-SeedVR2_VideoUpscaler - <a target="_blank" rel="ugc" href="https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler">https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler</a> - SEEDVR2 Video Upscaler Subgraph</li></ul><hr /><h3 id="models-and-downloads-(exact-paths)">Models &amp; Downloads (exact paths)</h3>The following list explains the base models I am most frequently using with this workflow. The list as well explains where to put each file after you downloaded it.1. Main Model (Flux.1 Dev GGUF):<ul><li>File: flux1-dev-Q5_1.gguf (or any other GGUF quant you prefer – Q4, Q5, Q6 or Q8 all work well)</li><li>Download: <a target="_blank" rel="ugc" href="https://huggingface.co/city96/FLUX.1-dev-gguf/resolve/main/flux1-dev-Q5_1.gguf">https://huggingface.co/city96/FLUX.1-dev-gguf/resolve/main/flux1-dev-Q5_1.gguf</a></li><li>Target folder: ComfyUI/models/diffusion_models/ (or Flux/ subfolder)</li></ul>2. Text Encoder (CLIP)<ul><li>File: t5xxl_fp8_e4m3fn.safetensors + clip_l.safetensors (standard Flux pair)</li><li>Download t5xxl: <a target="_blank" rel="ugc" href="https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors">https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors</a> Download clip_l: <a target="_blank" rel="ugc" href="https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors">https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors</a></li><li>Target folder: ComfyUI/models/clip/ or ComfyUI/models/text_encoders/</li></ul>3. VAE<ul><li>File: ae.safetensors</li><li>Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/flux1-dev/resolve/main/split_files/vae/ae.safetensors">https://huggingface.co/Comfy-Org/flux1-dev/resolve/main/split_files/vae/ae.safetensors</a></li><li>Target folder: ComfyUI/models/vae/</li></ul>4. Upscalers<ul><li>4× Upscaler: 4x-UltraSharp → <a target="_blank" rel="ugc" href="https://civarchive.com/models/116225/4x-ultrasharp">https://civarchive.com/models/116225/4x-ultrasharp</a></li><li>1× Skin-Contrast Upscaler: 1xSkinContrast-High-SuperUltraCompact.pth → <a target="_blank" rel="ugc" href="https://huggingface.co/notkenski/upscalers/blob/main/1xSkinContrast-High-SuperUltraCompact.pth">https://huggingface.co/notkenski/upscalers/blob/main/1xSkinContrast-High-SuperUltraCompact.pth</a></li><li>Target folder: ComfyUI/models/upscale_models/</li></ul>5. LoRAs (for NdSuperLoraLoader – full multi-LoRA support)<ul><li>Any Flux-compatible LoRA (.safetensors)</li><li>Target folder: ComfyUI/models/loras/</li></ul>6. SEEDVR2 Models (for the high-end upscaler subgraph – optional but recommended)<ul><li>DiT Model: seedvr2_ema_3b-Q8_0.gguf</li><li>VAE: ema_vae_fp16.safetensors</li><li>Download from the official ComfyUI-SeedVR2_VideoUpscaler repository or Hugging Face and place in the folders required by the custom node.</li></ul><hr /><h3 id="recommended-settings">Recommended Settings</h3>Sampler: Euler or Euler ancestral Scheduler: Simple, Normal or Beta Steps: 20–40 CFG Scale: 1.0 Flux Guidance: 3–6 Shift: 4–7 Resolution: freely selectable via the selectLatentSizePlus node (many golden-ratio-friendly presets included, swap orientation with one click)<hr /><h3 id="how-to-use-the-workflow">How to use the workflow</h3><ol><li>Load the JSON in ComfyUI.</li><li>Select your desired aspect ratio and resolution in the selectLatentSizePlus node (enable swap_orientation if needed).</li><li>Enter your prompt in the Positive Prompt node (the NdSuperLoraLoader will automatically pull trigger words from your LoRAs).</li><li>(Optional) Load one or more Flux-compatible LoRAs into the NdSuperLoraLoader – strengths and triggers are handled elegantly.</li><li>Generate. The first stage produces a high-quality base image.</li><li>(Optional) Run the SEEDVR2 upscaler subgraph for beautiful 2–4× upscales or even video. It works great on still images too.</li><li>The SaveImageExtended node gives you full control over filenames, metadata and folder structure.</li></ol>You can bypass the entire upscaler group if you just want fast test generations. The workflow also works with regular .safetensors Flux checkpoints – simply replace the UnetLoaderGGUF and DualCLIPLoader with the standard nodes.This is a clean, powerful and future-proof base for all your Flux.1 Dev work – whether you want fast single-LoRA portraits, complex multi-LoRA scenes or high-end upscaled output. I’ve been using it daily on my 6 GB card and it feels snappy and reliable.Huge thanks to WikkedAI for the original WikkedZITv4 foundation and to the creators of CacheDiT, SageAttention, NdSuperLoraLoader, selectLatentSizePlus and SeedVR2 for making low-VRAM Flux so enjoyable.If you have questions, feedback or want to share your results – I’m always happy to hear from you in the comments. Enjoy the workflow and happy creating!

Files with SHA256: b8cf0066d06c888eb6310a59ca9571b5614f294739555f270096a60523f61e82