🔧 NEURO HARMONY

Purpose: This workflow is designed to generate ultra-detailed RAW-style images using the RAW_Photography LoRA, ControlNet depth guidance, and multiple stages of high-resolution upscaling.

🧠 Core Components:

1. Model and LoRA

• UNET: flux_dev.safetensors (fp8)

• CLIP: clip_l.safetensors + t5xxl_fp16.safetensors

• LoRA: RAW_Photography.safetensors (enabled at 100%) Model page here: https://civarchive.com/models/1639720

• LoRA is integrated via the Power Lora Loader (rgthree) node.

2. Prompting and Detailing

• BilboXPhotoPrompt is used to generate rich photo-style prompts.

• A separate prompt detailer enhances:

  • high-frequency surface texture,

  • edge and contour definition,

  • natural gradients,

  • depth and occlusion cues,

  • realistic material response,

  • and framing clarity.

• FluxGuidance is applied with guidance: 3.5 to boost semantic conditioning.

3. Depth Guidance with ControlNet

• Preprocessor: MiDaS-DepthMapPreprocessor at 1280px resolution

• ControlNet: flux-depth-controlnet-v3.safetensors

• Used via ControlNetApplyAdvanced with settings:

  • Strength: 0.6

  • Start: 0.0

  • End: 0.618

This ensures stable structure and perspective.

4. Detail Enhancement via DetailDaemon

Three progressive sampling stages, each wrapped with a DetailDaemonSamplerNode using:

• detail_amount: 0.62

• start/end: 1

• bias: 0.62

• smooth: true

Sampling is handled through SamplerCustomAdvanced and BasicScheduler nodes using karras/beta scheduling and controlled denoising.

5. Hi-Res Upscaling

After each sampling pass, image resolution is progressively increased with:

• 002_lightweightSR_DIV2K_s64w8_SwinIR-S_x2.pth

• 001_classicalSR_DIV2K_s48w8_SwinIR-M_x4.pth

• 1xSkinContrast-SuperUltraCompact.pth — for final skin cleanup

All upscaling is performed with precision to preserve microtexture and avoid artifacts.

📸 Finalization and Output

• Results are compared using the Image Comparer (rgthree) in "Slide" mode.

• Images are saved with SaveImage for both intermediate and final outputs.

✅ Summary:

Flux_RAW_HIRes_V2 is a highly optimized multi-stage workflow tailored for photorealism and ultra-fine detail. It combines:

• a RAW photography LoRA,

• progressive DetailDaemon refinement,

• ControlNet depth stabilization,

• SwinIR upscaling layers,

• and enhanced semantic conditioning.

Ideal for portraits where skin detail, structure, and texture fidelity matter most.