This is a simple Text-to-Image workflow for the Moss model (dirtyMoss).It features a two-stage generation process:<ol><li>Initial generation at 768×1344</li><li>Light refine pass (denoise 0.35)</li><li>Upscale with remacri</li></ol>Generation speed: ~35–41 seconds per image on RTX 4060 Ti 16GB.Required models:<ul><li>UNET: dirtyMoss_int8.safetensors</li><li>CLIP: Qwen3.5-9B-heretic-v2-merged-int8-convrot.safetensors (moss_image type)</li><li>VAE: flux2-vae.safetensors</li><li>Upscaler: remacri_original.safetensors</li></ul>LoRAs used (via Power Lora Loader):<ul><li>cndamiph_Candid_Amateur_iPhone_MOSS_v1 (0.2)</li><li>8-steps-dmd2-lora (1.0)</li><li>realistic-moss-sft-nikastyle-moss-image-sft-epoch-15 (0.8)</li><li>PornMaster_Moss_Detail_Slider_V1 (4.0)</li></ul>Custom nodes:<ul><li>Power Lora Loader (rgthree)</li></ul>Because I'm very lazy, I didn't make it pretty and didn't group the nodes — it'll do as is. The workflow is very simple and straightforward.Just drop your prompt, queue, and enjoy. Works well for photorealistic portraits and full-body shots.

Files with SHA256: 370dcc50a1bc60c3f675d5d7b4f30873f9bc746dcc47b96df48163ca080da0a3