Ryan Dick
|
708a4f68da
|
Run FLUX VAE decoding in the user's preferred dtype rather than float32. Tested, and seems to work well at float16.
|
2024-08-22 18:16:43 +00:00 |
|
Ryan Dick
|
08633c3f04
|
Move prepare_latent_image_patches(...) to sampling.py with all of the related FLUX inference code.
|
2024-08-22 17:18:43 +00:00 |
|
Ryan Dick
|
4eca99574b
|
Rename field positive_prompt -> prompt.
|
2024-08-22 16:18:33 +00:00 |
|
Ryan Dick
|
a27250a95e
|
Add comment about incorrect T5 Tokenizer size calculation.
|
2024-08-22 16:09:46 +00:00 |
|
Ryan Dick
|
35d8e6a05b
|
Tidy is_schnell detection logic.
|
2024-08-22 16:03:54 +00:00 |
|
Ryan Dick
|
afd4913a1b
|
Make FLUX get_noise(...) consistent across devices/dtypes.
|
2024-08-22 15:56:30 +00:00 |
|
Ryan Dick
|
6afb1be872
|
Mark FLUX nodes as prototypes.
|
2024-08-22 15:29:59 +00:00 |
|
Brandon Rising
|
001d1b6e35
|
Attribute black-forest-labs/flux for much of the flux code
|
2024-08-21 15:54:07 -04:00 |
|
maryhipp
|
377fcaf49c
|
added FLUX dev to starter models
|
2024-08-21 15:47:19 -04:00 |
|
Brandon Rising
|
7861c1d779
|
Undo changes to the v2 dir of frontend types
|
2024-08-21 15:44:38 -04:00 |
|
Brandon Rising
|
3d251b4b93
|
Run ruff
|
2024-08-21 15:37:27 -04:00 |
|
Brandon Rising
|
fc760d3719
|
Remove automatic install of models during flux model loader, remove no longer used import function on context
|
2024-08-21 15:34:47 -04:00 |
|
Ryan Dick
|
0ce9faae7d
|
Fix max_seq_len field description.
|
2024-08-21 19:17:39 +00:00 |
|
Ryan Dick
|
42bbab74b3
|
Add docs to the quantization scripts.
|
2024-08-21 19:08:28 +00:00 |
|
Ryan Dick
|
203542c7a8
|
Update load_flux_model_bnb_llm_int8.py to work with a single-file FLUX transformer checkpoint.
|
2024-08-21 19:08:16 +00:00 |
|
Ryan Dick
|
7f62033f1f
|
Fix bug in InvokeInt8Params that was causing it to use double the necessary VRAM.
|
2024-08-21 19:08:00 +00:00 |
|
maryhipp
|
d2cb6889c5
|
add better workflow name
|
2024-08-21 14:52:23 -04:00 |
|
maryhipp
|
71088623a7
|
add better workflow description
|
2024-08-21 14:49:05 -04:00 |
|
maryhipp
|
25482c031b
|
fix(worker) fix T5 type
|
2024-08-21 14:45:46 -04:00 |
|
maryhipp
|
68a917aed5
|
update default workflow
|
2024-08-21 14:45:46 -04:00 |
|
Mary Hipp
|
04e861ba5a
|
fix schema
|
2024-08-21 14:41:58 -04:00 |
|
Mary Hipp
|
e063008246
|
tsc and lint fix
|
2024-08-21 14:36:44 -04:00 |
|
Mary Hipp
|
fe636bb6ca
|
feat(ui): create new field for t5 encoder models in nodes
|
2024-08-21 14:36:44 -04:00 |
|
Mary Hipp
|
ec6981a860
|
fix(ui): pass base/type when installing models, add flux formats to MM badges
|
2024-08-21 14:36:44 -04:00 |
|
Mary Hipp
|
d5a55789f9
|
fix(ui): only exclude flux main models from linear UI dropdown, not model manager list
|
2024-08-21 14:36:44 -04:00 |
|
maryhipp
|
09d1f75fe9
|
add FLUX schnell starter models and submodels as dependenices or adhoc download options
|
2024-08-21 14:27:35 -04:00 |
|
maryhipp
|
c095af65fb
|
add case for clip embed models in probe
|
2024-08-21 14:27:35 -04:00 |
|
maryhipp
|
2c72295b1c
|
update flux_model_loader node to take a T5 encoder from node field instead of hardcoded list, assume all models have been downloaded
|
2024-08-21 14:27:34 -04:00 |
|
Ryan Dick
|
e41025ddc7
|
Move requantize.py to the quatnization/ dir.
|
2024-08-21 18:21:44 +00:00 |
|
Ryan Dick
|
38c2e7801f
|
Add docs to the requantize(...) function explaining why it was copied from optimum-quanto.
|
2024-08-21 18:19:47 +00:00 |
|
Ryan Dick
|
d11dc6ddd0
|
Remove duplicate log_time(...) function.
|
2024-08-21 18:10:24 +00:00 |
|
Brandon Rising
|
8b0b496c2d
|
More flux loader cleanup
|
2024-08-21 12:37:25 -04:00 |
|
Brandon Rising
|
ada483f65e
|
Various styling and exception type updates
|
2024-08-21 11:59:04 -04:00 |
|
Brandon Rising
|
0913d062d8
|
Switch inheritance class of flux model loaders
|
2024-08-21 11:30:16 -04:00 |
|
Brandon Rising
|
d4872253a1
|
Update doc string for import_local_model and remove access_token since it's only usable for local file paths
|
2024-08-21 11:18:07 -04:00 |
|
Ryan Dick
|
e680cf76f6
|
Address minor review comments.
|
2024-08-21 13:45:22 +00:00 |
|
Ryan Dick
|
253b2b1dc6
|
Rename t5Encoder -> t5_encoder.
|
2024-08-21 13:27:54 +00:00 |
|
Mary Hipp
|
5edec7f105
|
add default workflow for flux t2i
|
2024-08-21 09:11:17 -04:00 |
|
Mary Hipp
|
ae9a1549ae
|
exclude flux models from main model dropdown
|
2024-08-21 09:11:17 -04:00 |
|
Brandon Rising
|
c819da8859
|
Some cleanup of the tags and description of flux nodes
|
2024-08-21 09:11:15 -04:00 |
|
Brandon Rising
|
e19f079cb2
|
Add t5 encoders and clip embeds to the model manager
|
2024-08-21 09:10:53 -04:00 |
|
Brandon Rising
|
dd24f83d43
|
Fix styling/lint
|
2024-08-21 09:10:22 -04:00 |
|
Brandon Rising
|
da766f5a7e
|
Fix support for 8b quantized t5 encoders, update exception messages in flux loaders
|
2024-08-21 09:10:22 -04:00 |
|
Ryan Dick
|
120e1cf1e9
|
Add tqdm progress bar to FLUX denoising.
|
2024-08-21 09:10:22 -04:00 |
|
Ryan Dick
|
5e2351f3bf
|
Fix FLUX output image clamping. And a few other minor fixes to make inference work with the full bfloat16 FLUX transformer model.
|
2024-08-21 09:10:22 -04:00 |
|
Brandon Rising
|
d705c3cf0e
|
Select dev/schnell based on state dict, use correct max seq len based on dev/schnell, and shift in inference, separate vae flux params into separate config
|
2024-08-21 09:10:20 -04:00 |
|
Brandon Rising
|
115f350f6f
|
Install sub directories with folders correctly, ensure consistent dtype of tensors in flux pipeline and vae
|
2024-08-21 09:09:39 -04:00 |
|
Brandon Rising
|
be6cb2c07c
|
Working inference node with quantized bnb nf4 checkpoint
|
2024-08-21 09:09:39 -04:00 |
|
Brandon Rising
|
4fb5529493
|
Remove unused param on _run_vae_decoding in flux text to image
|
2024-08-21 09:09:39 -04:00 |
|
Brandon Rising
|
b43ee0b837
|
Add nf4 bnb quantized format
|
2024-08-21 09:09:39 -04:00 |
|