Minimal flux with fp8 freeze - #6

Open

wkpark wants to merge 70 commits into

devfrom

minimal-flux-with-fp8-freeze

Commits on Oct 3, 2024

Fix typo
changeworld
committed
d8ad364

Commits on Oct 24, 2024

Fix DAT models download (#16302)
w-e-w
authored
984b952

Commits on Oct 25, 2024

chore(js): avoid lots of `Wake Lock is not supported.`
bluelovers
authored
ee0ad5c

Commits on Oct 26, 2024

Merge pull request #16523 from changeworld/fix/typo
w-e-w
authored
38c8043

Commits on Oct 27, 2024

Merge pull request #16588 from bluelovers/patch-3
w-e-w
authored
d88a3c1

Commits on Oct 29, 2024

image embedding data cache (#16556)
w-e-w
authored
deb3803
Allow newline in Extra Network activation text (#16428)
w-e-w
authored
820fe8d
extra_only / main_ui_only ScriptPostprocessing (#16374)
w-e-w
authored
0bf36cf
Fix postprocessing_enable_in_main_ui ScriptPostprocessing elem_id (#16373)
w-e-w
authored
4ec10bc
Disable Hires checkpoint if same as First pass checkpoint (#16269)
w-e-w
authored
14c6d6c
pyenv-win compatibility - another approach (#16287)
viking1304
authored
f31faf6
addEventListener {passive: false} (#16575)
w-e-w
authored
5948143
InputAccordion duplicate elem_id handling (#16381)
w-e-w
authored
5206b93
Fix weighting config for SDXL v-pred
catboxanon
authored
ac28cad
Fix Default system None filter logic (#16309)
w-e-w
authored
533c7b7
XYZ option to disable grid (#16416)
w-e-w
authored
28323cf
sd_xl_v.yaml: use_checkpoint = False
catboxanon
authored
e6f36d9

Commits on Oct 30, 2024

Merge pull request #16606 from AUTOMATIC1111/fix/vweighting
w-e-w
authored
aa52408
Warn if WebUI is installed under a dot directory (#16584)
w-e-w
authored
91de919
use shared.hf_endpoint (#16611)
w-e-w
authored
1b16c62

Commits on Nov 1, 2024

import Flux from https://github.com/black-forest-labs/flux/
wkpark
committed
853551b
add flux model wrapper
wkpark
committed
d38732e
fix for flux
wkpark
committed
2d1db1a
use empty_like for speed
wkpark
committed
821e76a
fix misc
wkpark
committed
39328bd
check Unet/VAE and load as is
wkpark
committed
c972951
simplified get_loadable_dtype
wkpark
committed
fcd609f
misc fixes to support float8 dtype_unet
wkpark
committed
537d9dd
add shared.opts.lora_without_backup_weight option to reduce ram usage
wkpark
committed
2060886
support copy option to reduce ram usage
wkpark
committed
2f72fd8
fix to support dtype_inference != dtype case
wkpark
committed
24f2c1b
preserve detected dtype_inference
wkpark
committed
477ff35
add diffusers weight mapping for flux lora
wkpark
committed
d6a609a
fix for Lora flux
wkpark
committed
51c2852
fix for t5xxl
wkpark
committed
7e2d519
vae fix for flux
wkpark
committed
9c0fd83
support Flux1
wkpark
committed
219a0e2
fix to support float8_*
wkpark
committed
9e57c72
add cheap approximation for flux
wkpark
committed
789bfc7
minor update
wkpark
committed
44a8480
pytest with --precision full --no-half
wkpark
committed
9617f15
fix lora without backup
wkpark
committed
3cdc26a
revert to use without_autocast()
wkpark
committed
3b18b6f
fix position_ids
wkpark
committed
2ffdf01
fix for float8_e5m2 freeze model
wkpark
committed
1e73a28
fix load_vae() to check size mismatch
wkpark
committed
1318f61
add fix_unet_prefix() to support unet only checkpoints
wkpark
committed
eee7294
use assign=True for some cases
wkpark
committed
6675d1f
check lora_unet prefix to support Black Forest Labs's lora
wkpark
committed
1f77922
call lowvram.send_everything_to_cpu() for interrupted case
wkpark
committed
380e9a8
call torch_gc() to fix VRAM usage spike when call decode_first_stage()
wkpark
committed
71b430f
use text_encoders.t5xxl.transformer.shared.weight tokens weights
wkpark
committed
f569f6e
fix flux to use float8 t5xxl
wkpark
committed
28eca46
fixed typo in the flux lora map
wkpark
committed
4bea93b
fixed ai-toolkit flux lora support
wkpark
committed
30d0f95
make Sd3T5 shared.opts.sd3_enable_t5 independent
wkpark
committed
11c9bc7
support Flux schnell and cleanup
wkpark
committed
8c9c139
fix some nn.Embedding to set dtype=float32 for some float8 freeze model
wkpark
committed
2e65335
use isinstance()
wkpark
committed
03516f4
use shared.opts.lora_without_backup_weight option in the devices.autocast()
wkpark
committed
ba499f9
do not use copy option for nn.Embedding
wkpark
committed
5f3314e
do not use assing=True for nn.LayerNorm
wkpark
committed
4ad5f22
flux: clean up some dead code
wkpark
committed
98cb284
task manager added
wkpark
committed
1d3dae1
reduce backup_weight size for float8 freeze model
wkpark
committed
0ab4d79
extract backup/restore io-bound operations out of forward hooks to speed up
wkpark
committed
04f9084
call gc.collect() when wanted_names == ()
wkpark
committed
2a1988f
backup only for needed weights required by lora
wkpark
committed
412401b
fix for lazy backup
wkpark
committed
b783a96
restore org_dtype != compute dtype case
wkpark
committed
310d0e6