CalamitousFelicitousness c605a1bb62 feat(taesd): add FLUX.2 preview support ...

Enable live preview during FLUX.2 and FLUX.2 Klein image generation
using the TAE FLUX.2 decoder from madebyollin/taesd.

- Add dedicated TAE entries (FLUX.1, FLUX.2, SD3) that auto-select
  based on model type, making the dropdown only affect SD/SDXL models
- Add FLUX.2 latent unpacking in callback to convert packed
  [B, seq_len, 128] format to spatial [B, 32, H, W] for preview
- Support FLUX.2's 32 latent channels (vs 16 for FLUX.1/SD3)

2026-01-16 03:01:52 +00:00

..

hybrid_small.py

refactor taesd and add multiple variants in settings

2025-01-12 14:09:55 -05:00

taehv.py

Fix Qwen VAE

2025-10-11 00:55:22 +03:00

taem1.py

add wan 2.1 text-to-image

2025-07-14 13:47:14 -04:00

taesd.py

feat(taesd): add FLUX.2 preview support

2026-01-16 03:01:52 +00:00