COMFY LABcomfy.yellorn.com
Yellorn Editor
Benchmarked on RTX 4070

ComfyUI Workflow Lab

Reverse-engineered AI artwork recipes verified on consumer hardware. Inspect clean canvas node graphs, study reproduction field notes, and download production-ready JSON files without fighting custom node errors.

Civitai #143353989: Slavic Woman in Pastel Bedroom (Sick Ollie Krea 2 + 11 LoRA Stack)
Sick Ollie (Krea 2 MXFP8 DiT)10GB+ VRAM9 steps · CFG 1

Civitai #143353989: Slavic Woman in Pastel Bedroom (Sick Ollie Krea 2 + 11 LoRA Stack)

Exact reproduction of Civitai #143353989 on RTX 4070. Chaining 11 sequential LoRA sliders on Sick Ollie (Krea 2 MXFP8 DiT) with Wan 2.1 16-channel VAE and Euler Ancestral beta sampling at 840x1256 in 9 steps.

Civitai #143439252 Original Stack: Sick Ollie Krea 2 + 9 LoRA Sliders
Sick Ollie (Krea 2 MXFP8 DiT)10GB+ VRAM8 steps · CFG 1

Civitai #143439252 Original Stack: Sick Ollie Krea 2 + 9 LoRA Sliders

Exact reproduction of Civitai #143439252 on RTX 4070. Chaining 9 sequential LoRA slider adapters on Sick Ollie (Krea 2 MXFP8) with Wan 2.1 VAE and Euler a beta sampling in 8 steps.

Paparazzi Direct Flash: Photorealistic Seductive Night Portrait
Qwen-Image-2.1 DiT (GGUF Q4_K_M)8GB+ VRAM35 steps · CFG 2.2

Paparazzi Direct Flash: Photorealistic Seductive Night Portrait

Reverse-engineered Civitai #143439252 recipe. Reproduces harsh on-camera flash, deep specular highlights on dewy skin, and sharp background wall shadows without needing 9 separate slider LoRAs.

Qwen-Image-2.1 Uncensored: GGUF DiT & Heretic Text Encoder
Qwen-Image-2.1 DiT (GGUF Q4_K_M)8GB+ VRAM35 steps · CFG 2.2

Qwen-Image-2.1 Uncensored: GGUF DiT & Heretic Text Encoder

Full canvas workflow combining GGUF-quantized Qwen-Image-2.1 diffusion weights with the refusal-ablated Heretic text encoder. Eliminates morality guardrails and runs smoothly on 12GB VRAM.

Flux.1 Dev Spicy Preset: Photorealistic Uncensored Denoising
FLUX.1-dev (FP8 / BF16)12GB+ VRAM28 steps · CFG 1

Flux.1 Dev Spicy Preset: Photorealistic Uncensored Denoising

High-fidelity Flux.1-dev canvas workflow with dual text encoders (CLIP L + T5xxl) and FP8 model precision. Optimized for intricate skin textures, natural folds, and anatomy accuracy.

Qwen-Image-2.1 Viggle Turbo: 4-Step Ultra-Fast DMD2 Distillation
Qwen-Image-2.1 Viggle Turbo (DMD2 4-Step)8GB+ VRAM4 steps · CFG 1

Qwen-Image-2.1 Viggle Turbo: 4-Step Ultra-Fast DMD2 Distillation

Rapid concept exploration workflow powered by Viggle Turbo DMD2 distilled checkpoint. Generates photorealistic high-resolution images in just 4 sampling steps with 1.8-second generation feedback.