Remove prompt from Flux refiner stage
This commit is contained in:
@@ -2,7 +2,9 @@
|
||||
|
||||
Two-stage local image-to-image workflow. Qwen NoctQ v4 generates the first
|
||||
image, then the decoded pixels are passed to FLUX.3 Klein as both the image
|
||||
reference and the VAE-encoded latent for a low-denoise refinement pass.
|
||||
reference and the VAE-encoded latent for a low-denoise refinement pass. The
|
||||
FLUX stage has **no prompt text**; it refines only from the supplied image
|
||||
conditioning and latent.
|
||||
|
||||
## Fixed starter settings
|
||||
|
||||
@@ -18,8 +20,8 @@ is used.
|
||||
|
||||
The input is `../character_reference.png` at 1080×1920 with seed `310101`.
|
||||
The Qwen output is decoded with the Qwen VAE, then connected to the FLUX
|
||||
reference conditioner and re-encoded with `flux2-vae.safetensors` before the
|
||||
0.11-denoise refiner pass.
|
||||
reference conditioner with an empty prompt and re-encoded with
|
||||
`flux2-vae.safetensors` before the 0.11-denoise refiner pass.
|
||||
|
||||
## Test matrix
|
||||
|
||||
|
||||
Reference in New Issue
Block a user