Ryan Dick
|
5e8cf9fb6a
|
Remove hack to clear cache from the FluxTextToImageInvocation. We now clear the cache based on the on-disk model size.
|
2024-08-29 19:08:18 +00:00 |
|
Ryan Dick
|
c738fe051f
|
Split T5 encoding and CLIP encoding into separate functions to ensure that all model references are locally-scoped so that the two models don't have to be help in memory at the same time.
|
2024-08-29 19:08:18 +00:00 |
|
Ryan Dick
|
29fe1533f2
|
Fix bug in InvokeLinear8bitLt that was causing old state information to persist after loading from a state dict. This manifested as state tensors being left on the GPU even when a model had been offloaded to the CPU cache.
|
2024-08-29 19:08:18 +00:00 |
|
Ryan Dick
|
77090070bd
|
Check the size of a model on disk and make room for it in the cache before loading it.
|
2024-08-29 19:08:18 +00:00 |
|
Ryan Dick
|
6ba9b1b6b0
|
Tidy up GIG -> GB and remove unused GIG constant.
|
2024-08-29 19:08:18 +00:00 |
|
Ryan Dick
|
c578b8df1e
|
Improve ModelCache docs.
|
2024-08-29 19:08:18 +00:00 |
|
Ryan Dick
|
cad9a41433
|
Remove unused MOdelCache.exists(...) function.
|
2024-08-29 19:08:18 +00:00 |
|
Ryan Dick
|
5fefb3b0f4
|
Remove unused param from ModelCache.
|
2024-08-29 19:08:18 +00:00 |
|
Ryan Dick
|
5284a870b0
|
Remove unused constructor params from ModelCache.
|
2024-08-29 19:08:18 +00:00 |
|
Ryan Dick
|
e064377c05
|
Remove default model cache sizes from model_cache_default.py. These defaults were misleading, because the config defaults take precedence over them.
|
2024-08-29 19:08:18 +00:00 |
|
Mary Hipp
|
3e569c8312
|
feat(ui): add fields for CLIP embed models and Flux VAE models in workflows
|
2024-08-29 11:52:51 -04:00 |
|
maryhipp
|
16825ee6e9
|
feat(nodes): bump version of flux model node, update default workflow
|
2024-08-29 11:52:51 -04:00 |
|
Mary Hipp
|
3f5340fa53
|
feat(nodes): add submodels as inputs to FLUX main model node instead of hardcoded names
|
2024-08-29 11:52:51 -04:00 |
|
chainchompa
|
326de55d3e
|
remove api changes and only preselect style preset
|
2024-08-28 09:53:29 -04:00 |
|
chainchompa
|
b2df909570
|
added selectedStylePreset to preload presets when app loads
|
2024-08-28 09:50:44 -04:00 |
|
chainchompa
|
026ac36b06
|
Revert "added selectedStylePreset to preload presets when app loads"
This reverts commit e97fd85904.
|
2024-08-28 09:44:08 -04:00 |
|
chainchompa
|
92125e5fd2
|
bug fixes
|
2024-08-27 16:13:38 -04:00 |
|
chainchompa
|
c0c139da88
|
formatting ruff
|
2024-08-27 15:46:51 -04:00 |
|
chainchompa
|
404ad6a7fd
|
cleanup
|
2024-08-27 15:42:42 -04:00 |
|
chainchompa
|
fc39086fb4
|
call stylePresetSelected
|
2024-08-27 15:34:31 -04:00 |
|
chainchompa
|
cd215700fe
|
added route for selecting style preset
|
2024-08-27 15:34:07 -04:00 |
|
chainchompa
|
e97fd85904
|
added selectedStylePreset to preload presets when app loads
|
2024-08-27 15:33:24 -04:00 |
|
Brandon Rising
|
0a263fa5b1
|
chore: bump version to v4.2.9rc1
|
2024-08-27 12:09:27 -04:00 |
|
Mary Hipp
|
fae3836a8d
|
fix CLIP
|
2024-08-27 10:29:10 -04:00 |
|
Mary Hipp
|
b3d2eb4178
|
add translations for new model types in MM, remove clip vision from filter since its not displayed in list
|
2024-08-27 10:29:10 -04:00 |
|
Ryan Dick
|
50085b40bb
|
Update starter model size estimates.
|
2024-08-26 20:17:50 -04:00 |
|
Mary Hipp
|
cff382715a
|
default workflow: add steps to exposed fields, add more notes
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
54d54d1bf2
|
Run ruff
|
2024-08-26 20:17:50 -04:00 |
|
Mary Hipp
|
e84ea68282
|
remove prompt
|
2024-08-26 20:17:50 -04:00 |
|
Mary Hipp
|
160dd36782
|
update default workflow for flux
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
65bb46bcca
|
Rename params for flux and flux vae, add comments explaining use of the config_path in model config
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
2d185fb766
|
Run ruff
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
2ba9b02932
|
Fix type error in tsc
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
849da67cc7
|
Remove no longer used code in the flux denoise function
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
3ea6c9666e
|
Remove in progress images until we're able to make the valuable
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
cf633e4ef2
|
Only install starter models if not already installed
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
bbf934d980
|
Remove outdated TODO.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
620f733110
|
ruff format
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
635d2f480d
|
ruff
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
70c278c810
|
Remove dependency on flux config files
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
56b9906e2e
|
Setup scaffolding for in progress images and add ability to cancel the flux node
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
a808ce81fd
|
Replace swish() with torch.nn.functional.silu(h). They are functionally equivalent, but in my test VAE deconding was ~8% faster after the change.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
83f82c5ddf
|
Switch the CLIP-L start model to use our hosted version - which is much smaller.
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
101de8c25d
|
Update t5 encoder formats to accurately reflect the quantization strategy and data type
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
3339a4baf0
|
Downgrade revert torch version after removing optimum-qanto, and other minor version-related fixes.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
dff4a88baa
|
Move quantization scripts to a scripts/ subdir.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
a21f6c4964
|
Update docs for T5 quantization script.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
97562504b7
|
Remove all references to optimum-quanto and downgrade diffusers.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
75d8ac378c
|
Update the T5 8-bit quantized starter model to use the BnB LLM.int8() variant.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
b9dd354e2b
|
Fixes to the T5XXL quantization script.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
33c2fbd201
|
Add script for quantizing a T5 model.
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
5063be92bf
|
Switch flux to using its own conditioning field
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
1047584b3e
|
Only import bnb quantize file if bitsandbytes is installed
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
6764dcfdaa
|
Load and unload clip/t5 encoders and run inference separately in text encoding
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
a0bf20bcee
|
Run FLUX VAE decoding in the user's preferred dtype rather than float32. Tested, and seems to work well at float16.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
14ab339b33
|
Move prepare_latent_image_patches(...) to sampling.py with all of the related FLUX inference code.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
25c91efbb6
|
Rename field positive_prompt -> prompt.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
1c1f2c6664
|
Add comment about incorrect T5 Tokenizer size calculation.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
d7c22b3bf7
|
Tidy is_schnell detection logic.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
185f2a395f
|
Make FLUX get_noise(...) consistent across devices/dtypes.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
0c5649491e
|
Mark FLUX nodes as prototypes.
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
94aba5892a
|
Attribute black-forest-labs/flux for much of the flux code
|
2024-08-26 20:17:50 -04:00 |
|
maryhipp
|
34451e5f27
|
added FLUX dev to starter models
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
1f9bdd1a9a
|
Undo changes to the v2 dir of frontend types
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
c27d59baf7
|
Run ruff
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
f130ddec7c
|
Remove automatic install of models during flux model loader, remove no longer used import function on context
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
a0a259eef1
|
Fix max_seq_len field description.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
b66f19d4d1
|
Add docs to the quantization scripts.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
4105a78b83
|
Update load_flux_model_bnb_llm_int8.py to work with a single-file FLUX transformer checkpoint.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
19a68afb3a
|
Fix bug in InvokeInt8Params that was causing it to use double the necessary VRAM.
|
2024-08-26 20:17:50 -04:00 |
|
maryhipp
|
fd68a2475b
|
add better workflow name
|
2024-08-26 20:17:50 -04:00 |
|
maryhipp
|
28ff7ba830
|
add better workflow description
|
2024-08-26 20:17:50 -04:00 |
|
maryhipp
|
5d0b248fdb
|
fix(worker) fix T5 type
|
2024-08-26 20:17:50 -04:00 |
|
maryhipp
|
01a4e0f6ef
|
update default workflow
|
2024-08-26 20:17:50 -04:00 |
|
Mary Hipp
|
91e0731506
|
fix schema
|
2024-08-26 20:17:50 -04:00 |
|
Mary Hipp
|
d1f904d41f
|
tsc and lint fix
|
2024-08-26 20:17:50 -04:00 |
|
Mary Hipp
|
269388c9f4
|
feat(ui): create new field for t5 encoder models in nodes
|
2024-08-26 20:17:50 -04:00 |
|
Mary Hipp
|
b8486379ce
|
fix(ui): pass base/type when installing models, add flux formats to MM badges
|
2024-08-26 20:17:50 -04:00 |
|
Mary Hipp
|
400eb94d3b
|
fix(ui): only exclude flux main models from linear UI dropdown, not model manager list
|
2024-08-26 20:17:50 -04:00 |
|
maryhipp
|
e210c96485
|
add FLUX schnell starter models and submodels as dependenices or adhoc download options
|
2024-08-26 20:17:50 -04:00 |
|
maryhipp
|
5f567f41f4
|
add case for clip embed models in probe
|
2024-08-26 20:17:50 -04:00 |
|
maryhipp
|
5fed573a29
|
update flux_model_loader node to take a T5 encoder from node field instead of hardcoded list, assume all models have been downloaded
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
cfac7c8189
|
Move requantize.py to the quatnization/ dir.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
1787de6836
|
Add docs to the requantize(...) function explaining why it was copied from optimum-quanto.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
ac96f187bd
|
Remove duplicate log_time(...) function.
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
72398350b4
|
More flux loader cleanup
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
df9445c351
|
Various styling and exception type updates
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
87b7a2e39b
|
Switch inheritance class of flux model loaders
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
f7e46622a1
|
Update doc string for import_local_model and remove access_token since it's only usable for local file paths
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
71f18353a9
|
Address minor review comments.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
4228de707b
|
Rename t5Encoder -> t5_encoder.
|
2024-08-26 20:17:50 -04:00 |
|
Mary Hipp
|
b6a05629ef
|
add default workflow for flux t2i
|
2024-08-26 20:17:50 -04:00 |
|
Mary Hipp
|
fbaa820643
|
exclude flux models from main model dropdown
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
db2a2d5e38
|
Some cleanup of the tags and description of flux nodes
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
8ba6e6b1f8
|
Add t5 encoders and clip embeds to the model manager
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
57168d719b
|
Fix styling/lint
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
dee6d2c98e
|
Fix support for 8b quantized t5 encoders, update exception messages in flux loaders
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
e49105ece5
|
Add tqdm progress bar to FLUX denoising.
|
2024-08-26 20:17:50 -04:00 |
|
Ryan Dick
|
0c5e11f521
|
Fix FLUX output image clamping. And a few other minor fixes to make inference work with the full bfloat16 FLUX transformer model.
|
2024-08-26 20:17:50 -04:00 |
|
Brandon Rising
|
a63f842a13
|
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
|
2024-08-26 20:17:50 -04:00 |
|