ahegao.redahegao.redComfyUI workflowsahegao.red home

ComfyUI · NSFW · 18+

Krea-2 NSFW ComfyUI workflow

The Image Pack runs on Krea-2, the open photorealistic image model by Krea, packaged for ComfyUI through Comfy-Org on Hugging Face. The pack ships the turbo int8 diffusion model, the Qwen Image VAE, an abliterated Qwen3-VL 4B text encoder, and a set of tuned LoRAs. It renders uncensored photorealistic images from a text prompt, and edits your photos while keeping the person intact. It runs on 16 GB of VRAM.

What the pack ships

ComponentFileNotes
Diffusion modelkrea2_turbo_int8_convrot.safetensors13.5 GB, fits a 16 GB card
Text encoderabliterated Qwen3-VL-4B, fp8Reads your prompt without refusals
VAEqwen_image_vae.safetensorsThe stock Qwen Image VAE
Tuned LoRAs4 quality LoRAs from our CivitaiLocked-in look and anatomy
Edit LoRAkrea2_identity_edit_v1_2Powers photo edits that keep the face

Everything installs with one command. Sampler, CFG, and LoRA settings arrive pre-calibrated. Leave them as they ship.

Text-to-image

Prompt in eight blocks: subject, outfit, pose, action, scenery, then the calibrated blocks camera, lighting, expression, and style. One concrete attribute per phrase beats vague adjectives.

Pick any aspect ratio from the resolution selector. Same seed and prompt reproduce the same image. Add your own LoRAs in the stack in row order.

Identity-preserving photo edits

Load a photo, write the change as a brief for a retoucher, and the workflow returns an edited version. The image defines who is in it. The prompt defines what changes.

  1. Describe the change, not the whole picture. "Recolor her tank top to white" works better than a full re-description.
  2. Pin identity-critical parts. Open or close with "same woman, same face, same pose" anchors.
  3. One edit per run. Stacking several changes invites drift.
  4. Stay at or below 2 megapixels. Larger canvases can bleed or duplicate source content.

For combining two people into one scene, the person goes into the reference input and the scene into the image input. If the result drifts from the source, raise ref_boost on the Krea2 Edit node.

Hardware

NVIDIA GPU with 16 GB+ VRAM (RTX 4070 Ti Super / 4080 / 5070 Ti / 5080 or better). On RunPod, RunPod RTX 4090. Disk needs 30 GB for models. Setup guides are linked below.

Adults only (18+). All sample output is synthetic, computer-generated fiction. Last verified October 2026.

Keep reading

PackImage PackGenerate photorealistic uncensored scenes and edit existing photos in one workflow, with identity-preserving editing. $49 one-time.PackVideo PackTurn any image into a clip with sound matched to the motion; motion-synced audio and likeness-preserving two-stage pipeline. $69 one-time.PackImage + Video PackBoth pipelines in one bundle: renders a high-resolution image, then animates it into a clip with sound while character and setting stay identical. $89 one-time.GuideComfyUI NSFW local setupInstall an ahegao.red ComfyUI workflow pack on Windows or Linux: one command installs Docker ComfyUI and every model file. Generate uncensored images and video on your own GPU.GuideComfyUI NSFW on RunPodRun an ahegao.red ComfyUI workflow pack on a rented RunPod GPU. Create a network volume, add credentials, deploy the official template, and connect on port 8188.GuideBest GPUs for NSFW AI generationWhat GPU do you need for uncensored AI image and video generation? VRAM requirements per pack, a card ladder, and when renting a RunPod card beats buying.Model notesMiniMax-H3 NSFW video workflowThe Video Pack runs MiniMax-H3, the open image-to-video model: your photo becomes a clip with a soundtrack matched to the motion. 32 GB VRAM local or rented on RunPod.Model notesAbliterated Qwen3-VL: uncensored prompt readingThe ahegao.red packs read prompts through abliterated Qwen3-VL models: the Image Pack ships Huihui-Qwen3-VL-4B, the Video Pack ships Qwen3-VL 32B. Safety filtering removed, fully local.
ahegao.red

© 2026 ahegao.red. All rights reserved.

All images and videos advertised on this page are computer-generated works of fiction. They do not depict any actual person, living or dead. All persons depicted therein are, and are represented as being, eighteen (18) years of age or older.