This includes the appendix and supplementay material for the paper: Ahmed Abuzuraiq, A., & Pasquier, P. (2026). Unboxing diffusion models for the arts: Interactive model bending and practice-based explainability. In Explainable AI for the Arts (XAIxArts). Springer. It includes sample results of systematic experiments with model bending (manipulation of generative model's internal activations for creative purposes) applied to a Stable Diffusion model using this ComfyUI plugin: https://github.com/abuzreq/ComfyUI-Model-Bending This repository includes two formats: a PDF version appendix containing the curated results mentioned in the paper, and a web viewer with a larger collection of results that can be interactivly sorted, grouped, and filtered. All the results are generated using the prompt “Analog style portrait of a person” with model realisticVisionV51_v51VAE.safetensors (seed 42; 20 steps; CFG 7; DPM++ 2M sampler; Karras scheduler; denoise 1; 512×512), while scaling each layer’s activations by 0, 0.5, 1.5, and 2. The experiment setup includes: (1) Same Prompt/Seed, Different Layers, (2) Same Prompt, Different Seeds , (3) Same Seed, Different Prompts, and (4) Same Seed/Prompt/Layer, Different Timesteps.