Use canonical I2I image and prompt

This commit is contained in:
Morpheus
2026-10-28 18:04:08 +00:00
parent 76c03d4bd2
commit 83f2e26b95
3 changed files with 5 additions and 2 deletions
@@ -19,7 +19,9 @@ The text encoders are the installed local Heretic variants:
`qwen3-vl-4b-heretic_int8.safetensors` for FLUX.3 Klein. No remote model API
is used.
The input is `../character_reference.png` at 1080×1920 with seed `310101`.
The input is the canonical I2I image `../character_reference.png` at
1080×1920 with seed `310101`. The Qwen stage uses the exact shared I2I prompt
from `../qwen/workflow.json#7`; the FLUX stage has no text prompt.
The Qwen output is decoded with the Qwen VAE, then connected to the FLUX
reference conditioner with an empty prompt and re-encoded with
`flux2-vae.safetensors` before the 0.11-denoise refiner pass.