Document ComfyUI workflow run records

optimized/README.md

@@ -39,7 +39,7 @@ These workflows are intended to become the practical default choices for each ca
 Each optimized workflow should have its own folder and usually include:
 
 - `workflow.json` or another portable Comfy workflow asset
-- `README.md`
+- `README.md` with a compact record of the parameters and graph changes that define the current master
 - optional notes, screenshots, or benchmark artifacts
 
 ## Notes layer
@@ -62,4 +62,5 @@ The weekly review should:
 - inspect newly collected workflows
 - decide whether a category master should be created or updated
 - document what changed and why
+- document the workflow settings that actually changed, especially prompt, negative prompt, CFG, steps, sampler, scheduler, seed, denoise, resolution, model swaps, LoRA weights, ControlNet wiring, and any node removals or additions
 - commit and push changes before reporting back

optimized/image-edit/README.md

@@ -6,3 +6,25 @@ Home for maintained category masters focused on image editing, inpainting, outpa
 
 - `zimage-turbo-3070-inpaint-start`
 - `flux2klein-9b-fp8-edit-master`
+
+## README rule
+
+Every image-edit master README should carry a compact run record for meaningful tuning changes.
+
+Minimum fields to record:
+
+- positive prompt
+- negative prompt
+- CFG
+- steps
+- sampler
+- scheduler
+- seed
+- denoise
+- resolution
+- checkpoint / model
+- VAE
+- LoRAs
+- ControlNets or other guidance nodes
+- mask or inpaint settings
+- node-level graph changes

optimized/image-edit/flux2klein-9b-fp8-edit-master/README.md

@@ -39,6 +39,28 @@ This is built from the official `9B distilled` template because it matches your
 - extra custom-node edits with unclear payoff
 - a fake outpainting claim before we prove it on your machine
 
+## Change Record
+
+Fill this out whenever the master is materially updated so we can see exactly what changed, not just that something changed.
+
+- Positive prompt: not recorded yet
+- Negative prompt: not recorded yet
+- CFG: not recorded yet
+- Steps: not recorded yet
+- Sampler: not recorded yet
+- Scheduler: not recorded yet
+- Seed: not recorded yet
+- Denoise: not recorded yet
+- Resolution: not recorded yet
+- Checkpoint / model: `models/diffusion_models/flux-2-klein-9b-fp8.safetensors`
+- VAE: `models/vae/flux2-vae.safetensors`
+- Text encoder(s): `models/text_encoders/qwen_3_8b_fp8mixed.safetensors`
+- LoRAs: none recorded yet
+- ControlNets / guidance nodes: none recorded yet
+- Masks / inpaint settings: not recorded yet
+- Node-level graph changes: stayed on the official `9B distilled` template route; no extra community graph surgery recorded yet
+- Why this change was made: keep the master aligned with your `9B fp8` preference while staying more practical than the heavier base route
+
 ## Required models
 
 - `models/diffusion_models/flux-2-klein-9b-fp8.safetensors`

optimized/image-edit/zimage-turbo-3070-inpaint-start/README.md

@@ -37,6 +37,28 @@ This master is a curated hold of the community inpainting workflow because it gi
 - any manual sampler surgery before real testing
 - any claim that this is better than `FLUX.2-klein` for edits
 
+## Change Record
+
+Fill this out whenever the master is materially updated so we can see exactly what changed, not just that something changed.
+
+- Positive prompt: not recorded yet
+- Negative prompt: not recorded yet
+- CFG: not recorded yet
+- Steps: not recorded yet
+- Sampler: community inpaint sampler path retained; exact values not recorded yet
+- Scheduler: not recorded yet
+- Seed: not recorded yet
+- Denoise: not recorded yet
+- Resolution: not recorded yet
+- Checkpoint / model: `models/diffusion_models/z_image_turbo_bf16.safetensors`
+- VAE: `models/vae/ae.safetensors`
+- Text encoder(s): `models/text_encoders/qwen_3_4b.safetensors`
+- LoRAs: none recorded yet
+- ControlNets / guidance nodes: `ZImageFunControlnet`
+- Masks / inpaint settings: inpainting-focused graph retained; exact mask settings not recorded yet
+- Node-level graph changes: held the community inpainting graph shape with `LanPaint_KSampler` and `ZImageFunControlnet`; no manual sampler surgery recorded yet
+- Why this change was made: keep a plausible real edit path on a `3070` without prematurely bloating the graph
+
 ## Required models
 
 - `models/text_encoders/qwen_3_4b.safetensors`

optimized/notes/process.md

@@ -33,3 +33,4 @@
 - What was removed
 - What was kept
 - What still needs Monday testing
+- The parameter-level change record for any promoted workflow: positive prompt, negative prompt, CFG, steps, sampler, scheduler, seed, denoise, resolution, checkpoint/model path, VAE, LoRAs, ControlNets, and any meaningful node rewiring