Brandon Rising
125b459e56
chore: 4.2.9rc2 version bump
2024-09-04 10:42:16 -04:00
Brandon Rising
33edee1ba6
Delete all flux bundle state dict keys when extracting the transformer state dict
2024-09-04 09:36:23 -04:00
Brandon Rising
d20335dabc
convert_bundle_to_flux_transformer_checkpoint now removes processed keys to decrease memory usage
2024-09-04 09:36:23 -04:00
Brandon Rising
d10d258213
Add a comment for why we're converting scale tensors in flux models to bfloat16
2024-09-04 09:36:23 -04:00
Brandon
d57ba1ed8b
Update invokeai/backend/model_manager/probe.py
...
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com >
2024-09-04 09:36:23 -04:00
Brandon Rising
2d0e34e57b
Support non-quantized bundles
2024-09-04 09:36:23 -04:00
Brandon Rising
a005d06255
feat: support checkpoint bundles containing more than just the transformer
2024-09-04 09:36:23 -04:00
Lincoln Stein
6dabe4d3ca
assign T5 encoder to base type "Any"
2024-09-03 15:55:51 -04:00
Lincoln Stein
00e4652d30
add more reliable fallback method for determining BnbQuantizedLlmInt8b
2024-09-03 15:55:51 -04:00
Lincoln Stein
b6434c5318
correct modelformat probe for t5 encoders
2024-09-03 15:55:51 -04:00
Lincoln Stein
3f7f9f8d61
add probes for T5_encoder and ClipTextModel
2024-09-03 15:55:51 -04:00
Brandon Rising
f3bb592544
Update latents used for preview images in flux
2024-09-03 14:04:16 -04:00
Brandon Rising
69f080fb75
Move flux step callback code into the step_callback util scripts, use other services within the invocation context
2024-09-03 14:04:16 -04:00
Brandon Rising
04272a7cc8
Initial attempt at preview images
2024-09-03 14:04:16 -04:00
Lincoln Stein
8d35af946e
[MM] add API routes for getting & setting MM cache sizes ( #6523 )
...
* [MM] add API routes for getting & setting MM cache sizes, and retrieving MM stats
* Update invokeai/app/api/routers/model_manager.py
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com >
* code cleanup after @ryand review
* Update invokeai/app/api/routers/model_manager.py
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com >
* fix merge conflicts; tested and working
---------
Co-authored-by: Lincoln Stein <lstein@gmail.com >
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com >
2024-09-02 12:18:21 -04:00
Ryan Dick
627b0bf644
Expose all FLUX model params in the default FLUX models.
2024-09-02 09:38:17 -04:00
Ryan Dick
b43da46b82
Rename 'FLUX VAE Encode'/'FLUX VAE Decode' to 'FLUX Image to Latents'/'FLUX Latents to Image'
2024-09-02 09:38:17 -04:00
Ryan Dick
4255a01c64
Restore line that was accidentally removed during development.
2024-09-02 09:38:17 -04:00
Ryan Dick
23adbd4002
Update schema.ts.
2024-09-02 09:38:17 -04:00
Ryan Dick
fb5a24fcc6
Update default workflows for FLUX.
2024-09-02 09:38:17 -04:00
Ryan Dick
cfdd5a1900
Rename flux_text_to_image.py -> flex_denoise.py
2024-09-02 09:38:17 -04:00
Ryan Dick
2313f326df
Add denoise_end param to FluxDenoiseInvocation.
2024-09-02 09:38:17 -04:00
Ryan Dick
2e092a2313
Rename FluxTextToImageInvocation -> FluxDenoiseInvocation.
2024-09-02 09:38:17 -04:00
Ryan Dick
763ef06c18
Use the existence of initial latents to decide whether we are doing image-to-image in the FLUX denoising node. Previously we were using the denoising_start value, but in some cases with an inpaintin mask you may want to run image-to-image from densoising_start=0.
2024-09-02 09:38:17 -04:00
Ryan Dick
8292f6cd42
Code cleanup and documentation around FLUX inpainting.
2024-09-02 09:38:17 -04:00
Ryan Dick
278bba499e
Split FLUX VAE decoding out into its own node from LatentsToImageInvocation.
2024-09-02 09:38:17 -04:00
Ryan Dick
dd99ed28e0
Split FLUX VAE encoding out into its own node from ImageToLatentsInvocation.
2024-09-02 09:38:17 -04:00
Ryan Dick
9a8aca69bf
Get a rough version of FLUX inpainting working.
2024-09-02 09:38:17 -04:00
Ryan Dick
7ad62512eb
Update MaskTensorToImageInvocation to support input mask tensors with or without a channel dimension.
2024-09-02 09:38:17 -04:00
Ryan Dick
bd466661ec
Remove unused vae field from FLUXTextToImageInvocation.
2024-09-02 09:38:17 -04:00
Ryan Dick
7ebb509d05
Bump FLUX node versions after splitting out VAE encode/decode.
2024-09-02 09:38:17 -04:00
Ryan Dick
0aa13c046c
Split VAE decoding out from the FLUXTextToImageInvocation.
2024-09-02 09:38:17 -04:00
Ryan Dick
a7a33d73f5
Get FLUX non-masked image-to-image working - still rough.
2024-09-02 09:38:17 -04:00
Ryan Dick
ffa39857d3
Add FLUX VAE decoding support to LatentsToImageInvocation.
2024-09-02 09:38:17 -04:00
Ryan Dick
e85c3bc465
Add FLUX VAE support to ImageToLatentsInvocation.
2024-09-02 09:38:17 -04:00
Brandon Rising
d62310bb5f
Support HF repos with subfolders in source on windows OS
2024-08-30 19:31:42 -04:00
Brandon Rising
1835bff196
Fix source string in hugging face installs with subfolders
2024-08-30 19:31:42 -04:00
Ryan Dick
4e4b6c6dbc
Tidy variable management and dtype handling in FluxTextToImageInvocation.
2024-08-29 19:08:18 +00:00
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
