Krea 2 Turbo 2-Step Distillation LoRA

Requirements

• NVIDIA RTX 30XX / 40XX / 50XX GPU
• CUDA-compatible GPU — FP8 for 16 GB+, or a GGUF quant for smaller cards
• At least 20 GB free storage

Model downloads

• lvladikov https://huggingface.co/lvladikov/Krea2-Turbo-Distill-2step-LoRA ⧉
• Krea 2 Turbo FP8 – the workflow default https://huggingface.co/AlperKTS/Krea2_FP8/tree/main ⧉
• Krea 2 Turbo GGUF – low VRAM option, pick your quant https://huggingface.co/vantagewithai/Krea-2-Turbo-GGUF/tree/main ⧉
• qwen3vl_4b_fp8_scaled.safetensors https://huggingface.co/Comfy-Org/Qwen3-VL/tree/main/text_encoders ⧉
• qwen_image_vae.safetensors https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae ⧉
• krea2_turbo_2step_rank_64_lora_comfyui.safetensors – lvladikov/Krea2-Turbo-Distill-2step-LoRA https://huggingface.co/lvladikov/Krea2-Turbo-Distill-2step-LoRA/tree/main ⧉

Custom nodes

• ComfyUI Manager https://github.com/ltdrdata/ComfyUI-Manager ⧉
• ComfyUI-GGUF (for the GGUF loader path) https://github.com/city96/ComfyUI-GGUF ⧉
• rgthree-comfy https://github.com/rgthree/rgthree-comfy ⧉

Setup steps

1. Download the free workflow .json with the button above.
2. Download the 6 model file(s) listed above into their ComfyUI model folders.
3. Install the 3 custom node(s) listed above via ComfyUI Manager, then fully restart ComfyUI.
4. Drag the workflow .json onto the ComfyUI canvas and confirm each loader node has the right model selected.
5. Run it. If a node shows red, update ComfyUI and restart before troubleshooting anything else.

Notes & tips

• What's in the Workflow: GGUF loader path alongside the default FP8, so you can run a quantized model on lower-VRAM cards (toggle with the Fast Groups Bypasser).; Resolution Selector for quick aspect-ratio and size presets.; Upscale nodes for a clean high-res pass after the fast base generation.
• Load the workflow and pick your model path — FP8 (default) or GGUF — with the Fast Groups Bypasser.
• Settings: steps 2, cfg 1.0 (Turbo is CFG-free), LoRA strength 1.0.
• The negative prompt is a ConditioningZeroOut — at cfg 1.0 there's nothing to write in it.
• At 2 steps you're in fast-preview territory — great for dialing in composition and prompt quickly. If you want a touch more refinement, the same creator's 4-step LoRA is the next tier up.
• Use the upscale pass for a clean higher-res result after the fast base generation.
• Since the LoRA is a work in progress, occasionally re-download to pick up newer versions.
• More Krea 2: FREE Krea 2 Turbo 4-Step LoRA (a bit more refinement) - (link); ComfyUI Krea 2 All-in-One Installer (Patreon) — now includes this 2-step LoRA, plus the Identity Edit and Depth ControlNet workflows, all set up automatically - https://www.patreon.com/TheLocalLab/posts/krea-2-all-in-6-163760558; Krea 2 RunPod Template - https://get.runpod.io/Krea2-ComfyUI

More resources

• ComfyUI Krea 2 All-in-One Installer (Patreon) — now includes this 2-step LoRA, plus the Identity Edit and Depth ControlNet workflows, all set up automatically https://www.patreon.com/TheLocalLab/posts/krea-2-all-in-6-163760558 ⧉
• Krea 2 RunPod Template https://get.runpod.io/Krea2-ComfyUI ⧉