A refined and enhanced workflow by Experimental_dAIver.This workflow brings the impressive quality, prompt adherence and efficiency of the new Krea 2 Turbo model family into your local ComfyUI setup. It is specifically optimized for low-VRAM GPUs (tested on RTX 4050 6 GB) and features the powerful NdSuperLoraLoader for seamless multi-LoRA stacking with automatic trigger-word handling, CacheDiT_Model_Optimizer + PathchSageAttentionKJ for noticeable speed gains, the intuitive selectLatentSizePlus aspect-ratio and resolution selector, ModelSamplingAuraFlow with shift control, and a complete integrated SEEDVR2 Video Upscaler Subgraph for outstanding 4K+ stills and short video sequences. The workflow uses the dedicated krea2 CLIP type together with qwen_image_vae for maximum compatibility and quality.Version 1.0 is the initial public release and delivers a clean, fast and highly flexible base specifically tuned for Krea 2 Turbo (and Base) checkpoints.To use Krea2, you need the latest ComfyUI versions 0.25 and later.Key features in v1.0:<ul><li>Full native support for Krea2_Turbo_fp8mixed.safetensors and all other quantized variants (FP8 / MXFP8 / NVFP4 / INT8 / ConvRot INT8) from the Winnougan collection</li><li>NdSuperLoraLoader (nd-super-nodes) with full multi-LoRA support, auto-fetch trigger words and clean strength control</li><li>CacheDiT_Model_Optimizer + PathchSageAttentionKJ – both optional but enabled by default for significant speed improvements on low-VRAM hardware with almost no quality loss</li><li>selectLatentSizePlus – convenient aspect-ratio and resolution selector with photography presets (including golden-ratio-friendly options) and one-click orientation swap</li><li>Advanced sampling via KSamplerAdvanced (ER_SDE or Euler) + ModelSamplingAuraFlow (shift 4 recommended) with Beta or Simple scheduler – excellent results already at 8–10 steps</li><li>High-quality decoding with qwen_image_vae</li><li>Complete SEEDVR2 Video Upscaler Subgraph – powerful DiT-based upscaler that delivers stunning high-resolution results on still images and short video clips, with Lab color correction, temporal settings and intelligent resolution handling</li><li>Professional output options with SaveImageExtended and ChronoSaveForCivit (perfect for direct CivitAI uploads with embedded metadata and workflow)</li><li>Self-documenting workflow containing a detailed MarkdownNote with all download links, recommended settings and folder guidance</li></ul><hr /><h3 id="required-custom-nodes">Required Custom Nodes</h3><ul><li>nd-super-nodes (HenkDz) – NdSuperLoraLoader and modern UI components <a target="_blank" rel="ugc" href="https://github.com/HenkDz/nd-super-nodes">https://github.com/HenkDz/nd-super-nodes</a></li><li>ComfyUI-CacheDiT – CacheDiT_Model_Optimizer</li><li>comfyui-kjnodes – PathchSageAttentionKJ</li><li>ComfyUi-MzMaXaM – selectLatentSizePlus <a target="_blank" rel="ugc" href="https://github.com/MzMaXaM/ComfyUi-MzMaXaM">https://github.com/MzMaXaM/ComfyUi-MzMaXaM</a></li><li>save-image-extended-comfyui – SaveImageExtended</li><li>ComfyUI-SeedVR2_VideoUpscaler – full SEEDVR2 Video Upscaler subgraph <a target="_blank" rel="ugc" href="https://github.com/ainvfx/ComfyUI-SeedVR2_VideoUpscaler">https://github.com/ainvfx/ComfyUI-SeedVR2_VideoUpscaler</a></li></ul>Important: Update ComfyUI to the latest version before installing the custom nodes. Krea 2 support and the involved nodes benefit greatly from recent core updates.<hr /><h3 id="models-and-downloads-(exact-paths)">Models &amp; Downloads (exact paths)</h3>The following list explains exactly which files you need and where to place them.1. Main Diffusion Model (Krea 2 Turbo FP8):File: Krea2_Turbo_fp8mixed.safetensors (or any other quant variant you prefer) Download: All quantized models (FP8 / MXFP8 / NVFP4 / INT8 / ConvRot INT8) for both Base and Turbo: 👉 <a target="_blank" rel="ugc" href="https://huggingface.co/Winnougan/Krea-2-Base-Turbo-NVFP4-FP8-INT8">Winnougan/Krea-2-Base-Turbo-NVFP4-FP8-INT8</a> Target folder: ComfyUI/models/diffusion_models/Krea2/ (Create the Krea2 subfolder if it does not exist. The UNETLoader references this exact path structure.)2. Text Encoder:File: qwen3vl_4b_fp8_scaled.safetensors Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Qwen3-VL/blob/main/text_encoders/qwen3vl_4b_fp8_scaled.safetensors">https://huggingface.co/Comfy-Org/Qwen3-VL/blob/main/text_encoders/qwen3vl_4b_fp8_scaled.safetensors</a> Target folder: ComfyUI/models/text_encoders/Important: In the CLIPLoader node set the type widget to krea2.3. VAE:File: qwen_image_vae.safetensors Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/blob/main/split_files/vae/qwen_image_vae.safetensors">https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/blob/main/split_files/vae/qwen_image_vae.safetensors</a> Target folder: ComfyUI/models/vae/4. LoRAs (for NdSuperLoraLoader – full multi-LoRA support):Any compatible LoRAs (.safetensors). Target folder: ComfyUI/models/loras/5. SEEDVR2 Models (for the integrated upscaler subgraph – optional but highly recommended):<ul><li>DiT Model: seedvr2_ema_3b-Q8_0.gguf</li><li>VAE: ema_vae_fp16.safetensors</li></ul>Download from the official ComfyUI-SeedVR2_VideoUpscaler repository or Hugging Face and follow the node’s installation instructions.<hr /><h3 id="folder-structure-overview">Folder Structure Overview</h3>text<pre><code>📂 ComfyUI/
├── 📂 models/
│ ├── 📂 diffusion_models/
│ │ └── 📂 Krea2/
│ │ └── Krea2_Turbo_fp8mixed.safetensors
│ ├── 📂 text_encoders/
│ │ └── qwen3vl_4b_fp8_scaled.safetensors
│ ├── 📂 vae/
│ │ └── qwen_image_vae.safetensors
│ └── 📂 loras/
│ └── (your LoRAs here)</code></pre><hr /><h3 id="recommended-settings">Recommended Settings</h3><ul><li>Sampler: er_sde (recommended) or euler</li><li>Scheduler: beta (recommended) or simple</li><li>Steps: 8–10 (Turbo model delivers excellent quality at very low step counts)</li><li>CFG Scale: 1.0</li><li>Shift (ModelSamplingAuraFlow): 4–7 (4 is the sweet spot in most cases)</li><li>Resolution &amp; Aspect Ratio: Freely selectable via selectLatentSizePlus – includes “2:3 Standard Photography”, many other standard ratios and resolutions up to 2048 px. Use swap_orientation for instant portrait/landscape flip. Batch size supported.</li><li>LoRA Strengths: Start with 0.6–1.0 per LoRA when stacking multiple models.</li></ul>A compact settings table is also embedded directly in the workflow’s MarkdownNote node for quick reference.<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 automatically handles trigger words from your LoRAs).</li><li>Load one or more compatible LoRAs into the NdSuperLoraLoader.</li><li>Generate. The workflow produces a high-quality base image extremely efficiently.</li><li>(Optional) Run the integrated SEEDVR2 upscaler subgraph for beautiful high-resolution results on still images or short video sequences.</li><li>Use SaveImageExtended and/or ChronoSaveForCivit for full filename control, metadata embedding and CivitAI-ready exports.</li></ol>You can bypass or mute the upscaler group completely for fast testing. The workflow also works with other Krea 2 checkpoints – simply change the filename in the UNETLoader. CacheDiT and SageAttention can be disabled individually if you ever encounter compatibility issues (they are optional speed boosters).This is a clean, fast and powerful base specifically tuned for the new Krea 2 Turbo FP8 model — perfect for quick iterations, creative multi-LoRA compositions and high-quality final outputs even on modest hardware.Huge thanks to Winnougan for creating and quantizing the excellent Krea 2 models, and to HenkDz (nd-super-nodes), the CacheDiT team, kjnodes, MzMaXaM, ainvfx (SeedVR2), as well as the authors of SaveImageExtended and ChronoSaveForCivit for making these advanced, low-VRAM workflows possible.If you have questions or want to share your results — I’m happy to hear from you in the comments. Enjoy the workflow!

Files with SHA256: 95e0ed4a0d7b264eea08e8408902c8e67806bd3e84cca57726a5d99e22337ae0