chris.dumas/comfyui-workflows
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update flux2klein smoke record and zimage notes

Browse Source
This commit is contained in:
Morpheus
2026-08-28 02:09:44 +00:00
parent 972bc2788c
commit 3a1f72ef43
9 changed files with 682 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
optimized/image-edit/flux2klein-9b-fp8-edit-master/README.md
+6 -6
View File
@@ -46,20 +46,20 @@ Fill this out whenever the master is materially updated so we can see exactly wh
- Positive prompt: not recorded yet
- Negative prompt: not recorded yet
- CFG: not recorded yet
- Steps: not recorded yet
- Sampler: not recorded yet
- CFG: `1`
- Steps: `4`
- Sampler: `euler`
- Scheduler: not recorded yet
- Seed: not recorded yet
- Seed: `26416064315367`
- Denoise: not recorded yet
- Resolution: not recorded yet
- Resolution: `1536x864`
- Checkpoint / model: `models/diffusion_models/flux-2-klein-9b-fp8.safetensors`
- VAE: `models/vae/full_encoder_small_decoder.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: aligned both saved diffusion-model widgets to the real `flux-2-klein-9b-fp8.safetensors` filename and kept the shared `full_encoder_small_decoder.safetensors` VAE; no extra community graph surgery recorded yet
- Node-level graph changes: aligned both saved diffusion-model widgets to the real `flux-2-klein-9b-fp8.safetensors` filename and kept the shared `full_encoder_small_decoder.safetensors` VAE; the 2026-08-27 single-image smoke held cleanly at `4` steps, `cfg 1`, `1536x864`, with `euler` and noise seed `26416064315367`
- Smoke test: `2026-08-27`, `4` steps, `cfg 1`, `1536x864`, output `benchmarks/flux2klein/runs/2026-08-27T02-08-31-134Z-single-smoke/cases/case01/01-flux2klein-overnight-smoke_00002_.png`
- Why this change was made: keep the master aligned with your `9B fp8` preference and the actual saved model filenames while staying more practical than the heavier base route
optimized/image-edit/zimage-turbo-3070-inpaint-start/README.md
+3 -3
View File
@@ -50,19 +50,19 @@ Fill this out whenever the master is materially updated so we can see exactly wh
- Seed: not recorded yet
- Denoise: not recorded yet
- Resolution: not recorded yet
- Checkpoint / model: `models/diffusion_models/z_image_turbo_bf16.safetensors`
- Checkpoint / model: `models/diffusion_models/zImageTurbo_turbo.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
- Node-level graph changes: held the community inpainting graph shape with `LanPaint_KSampler` and `ZImageFunControlnet`; the live loader resolves to `zImageTurbo_turbo.safetensors` even though the embedded source metadata still labels the split-file `z_image_turbo_bf16.safetensors`
- 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`
- `models/diffusion_models/z_image_turbo_bf16.safetensors`
- `models/diffusion_models/zImageTurbo_turbo.safetensors`
- `models/vae/ae.safetensors`
## Required custom nodes