Fix flux2klein fp8 master labels

This commit is contained in:
Morpheus
2026-08-23 02:09:00 +00:00
parent a16fbf315c
commit 026ca23043
11 changed files with 682 additions and 17 deletions
@@ -54,20 +54,20 @@ Fill this out whenever the master is materially updated so we can see exactly wh
- 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`
- 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: stayed on the official `9B distilled` template route; 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; no extra community graph surgery recorded yet
- Smoke test: `2026-08-21`, `4` steps, `cfg 1`, `1536x864`, output `benchmarks/flux2klein/runs/2026-08-21T02-03-28-751Z-single-smoke/cases/case01/01-flux2klein-overnight-smoke_00001_.png`
- Why this change was made: keep the master aligned with your `9B fp8` preference while staying more practical than the heavier base route
- 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
## Required models
- `models/diffusion_models/flux-2-klein-9b-fp8.safetensors`
- `models/text_encoders/qwen_3_8b_fp8mixed.safetensors`
- `models/vae/flux2-vae.safetensors`
- `models/vae/full_encoder_small_decoder.safetensors`
## Required custom nodes