Version 1 is a very simple txt2img Krea2 Workflow that does not have a upscale step. Version 2 upscales with SeedVR2 and then with ZImage which is what I found to give the best results. ZImage acts as a upscale fix based on my testing. See this post about V3 <a target="_blank" rel="ugc" href="https://civarchive.com/articles/36952/krea-2-on-12gb-vram-what-actually-improved-my-workflow-and-what-didnt">https://civarchive.com/articles/36952/krea-2-on-12gb-vram-what-actually-improved-my-workflow-and-what-didnt</a>V3<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0d203c92-4fa9-4068-8d26-b537e2927077/original=true/0d203c92-4fa9-4068-8d26-b537e2927077.jpeg" /> For a first-time user:<ul><li>Use a current ComfyUI version with Krea 2 and native SeedVR2 support. Older installations may show missing nodes. <a target="_blank" rel="ugc" href="https://docs.comfy.org/tutorials/image/krea/krea-2">Krea setup guide</a>.</li><li>Install the custom nodes: <a target="_blank" rel="ugc" href="https://github.com/willmiao/ComfyUI-Lora-Manager">LoRA Manager</a>, Image Saver, and <a target="_blank" rel="ugc" href="https://github.com/ylchen333/ComfyUI-VOSR2">ComfyUI-VOSR2</a>.</li><li>Download the models separately. The workflow JSON contains no weights. It needs the Krea checkpoint, Qwen text encoder, Sharp Plus VAE, SeedVR2 model/VAE, and VOSR2 bundle. Download the selected LoRAs or remove/disable their entries.</li><li>Check every model dropdown after importing. Their local filenames may differ from yours.</li><li>Expect substantial downloads and memory use. VOSR2 alone downloads roughly 7 GB on first use. Your 12 GB RTX 4070 runs the configured workflow, but that isn’t a tested minimum specification.</li><li>The saved resolution is 1248×1824 → 2496×3648. Both downstream resize nodes use fixed dimensions; changing the base size alone won’t automatically change the final size.</li></ul>V1 <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0c0a7632-2ea4-452f-a59d-8b22f4a25524/original=true/0c0a7632-2ea4-452f-a59d-8b22f4a25524.jpeg" />

Files with SHA256: 0f839b1c89089809491e8038ce8e2e4e2d29b044fb7c45d02f8df6856f70a809