f05ee56b2f
Fix docstring of community pipeline imagic ( #7062 )
2024-02-23 09:37:52 -08:00
34cc7f9b98
Fix typos ( #7068 )
2024-02-23 09:24:51 -08:00
53605ed00a
[Refactor] save_model_card function in text_to_image examples ( #7051 )
...
* Refactor save_model_card function to handle images and repo_folder parameters
* Discard changes to examples/text_to_image/train_text_to_image.py
* Discard changes to examples/text_to_image/train_text_to_image_lora_sdxl.py
* Update train_text_to_image_lora.py
* Update train_text_to_image_sdxl.py
2024-02-23 20:57:37 +05:30
bb1b76d3bf
IPAdapterTesterMixin ( #6862 )
...
* begin IPAdapterTesterMixin
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-02-22 14:25:33 -10:00
e4b8f173b9
re-add unet refactor PR ( #7044 )
...
* add
* remove copied from
---------
Co-authored-by: ultranity <1095429904@qq.com >
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2024-02-21 22:00:32 -10:00
f0216b7756
allow explicit tokenizer & text_encoder in unload_textual_inversion ( #6977 )
...
* allow passing tokenizer & text_encoder to unload_textual_inversion
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: Fabio Rigano <fabio2rigano@gmail.com >
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com >
2024-02-21 16:53:25 -10:00
d5f444de4b
Update checkpoint_merger pipeline to pass the "variant" argument ( #6670 )
...
* make checkpoint_merger pipeline pass the "variant" argument to from_pretrained()
* make style
---------
Co-authored-by: Lincoln Stein <lstein@gmail.com >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-02-21 15:45:50 -10:00
5a54dc9e95
Fix typos in text_to_image examples ( #7050 )
...
Update copyright information and fix typos in text_to_image examples
2024-02-21 16:40:45 -08:00
6fedbd850a
fix doc example for fom_single_file ( #7015 )
...
* fix doc
* remove use_safetensors from signature
* more
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2024-02-21 19:11:21 +05:30
1b3cfb1b10
update header ( #6596 )
...
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
2024-02-20 10:09:15 -08:00
af13a90ebd
Remove disable_full_determinism from StableVideoDiffusion xformers test. ( #7039 )
...
* update
* update
2024-02-20 21:43:23 +05:30
3067da1261
Fix load_model_dict_into_meta for ControlNet from_single_file ( #7034 )
...
update
2024-02-20 11:01:02 +05:30
6bceaea3fe
Update ControlNet Inpaint single file test ( #7022 )
...
update
2024-02-20 10:58:30 +05:30
baf9924be7
Fix alt text and image links in AnimateLCM docs ( #7029 )
...
update
2024-02-20 08:30:44 +05:30
d8d208acde
Supper IP Adapter weight loading in StableDiffusionXLControlNetInpaintPipeline ( #7031 )
...
* support ip adapter loading
* fix style
2024-02-19 09:44:35 -10:00
e0f33dfca4
IP-Adapter support for StableDiffusionXLControlNetInpaintPipeline ( #6941 )
...
* add ip-adapter support
* support ip image embeds
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-02-19 08:20:24 -10:00
15b125bb0e
Add section on AnimateLCM to docs ( #7024 )
...
* update
* update
* update
2024-02-19 22:20:37 +05:30
12004bf3a7
[Community Pipelines]Accelerate inference of stable diffusion xl (SDXL) by IPEX on CPU ( #6683 )
...
* add stable_diffusion_xl_ipex community pipeline
* make style for code quality check
* update docs as suggested
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com >
2024-02-19 13:39:08 +01:00
d2fc5ebb95
[Refactor] FreeInit for AnimateDiff based pipelines ( #6874 )
...
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
2024-02-19 11:11:42 +05:30
779eef95b4
[from_single_file] pass torch_dtype to set_module_tensor_to_device ( #6994 )
...
fix
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2024-02-19 10:09:19 +05:30
d5b8d1ca04
Fix Pixart Slow Tests ( #6962 )
...
* update
* update
2024-02-19 09:50:18 +05:30
eba7e7a6d7
IP-Adapter attention masking ( #6847 )
...
* Add attention masking to attn processors
* Update tensor conversion
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-02-18 18:06:14 -10:00
31de879fb4
[IP2P] Make text encoder truly optional in InstructPi2Pix ( #6995 )
...
* make text encoder component truly optional.
* more fixes
* Apply suggestions from code review
Co-authored-by: YiYi Xu <yixu310@gmail.com >
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-02-18 20:21:22 +05:30
07349c25fe
Fix deprecation warning for torch.utils._pytree._register_pytree_node in PyTorch 2.2 ( #7008 )
...
Fixed deprecation warning for torch.utils._pytree._register_pytree_node in PyTorch 2.2
Co-authored-by: Yinghua <yzho0423@uni.sydney.edu.au >
2024-02-18 20:11:33 +05:30
8974c50bff
[SVD] fix a bug when passing image as tensor ( #6999 )
...
* fix
* update docstring
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2024-02-17 23:10:31 -10:00
c18058b405
Fixed typos in dosctrings of __init__() and in forward() of Unet3DConditionModel ( #6663 )
...
* Fixed typos in __init__ and in forward of Unet3DConditionModel
* Resolving conflicts
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-02-17 21:56:16 -10:00
2938d5a672
Add documentation for strength parameter in Controlnet_img2img pipelines ( #6951 )
...
copy docstring for `strength` from stablediffusion img2img pipeline to controlnet img2img pipelines
2024-02-17 21:47:02 -10:00
d4ade821cd
start depcrecation cycle for lora_attention_proc 👋 ( #7007 )
2024-02-18 13:11:30 +05:30
3a7e481611
[docs] Video generation ( #6701 )
...
* first draft
* fix path
* fix path
* i2vgen-xl
* review
* modelscopet2v
* feedback
2024-02-16 16:35:37 -08:00
d649d6c6f3
[docs] Fix callout ( #6998 )
...
Update ip_adapter.md
2024-02-16 10:37:12 -10:00
777063e1bf
Update textual_inversion.py ( #6952 )
...
* Update textual_inversion.py
* Apply suggestions from code review
* Update textual_inversion.py
* Update textual_inversion.py
* Update textual_inversion.py
* Update textual_inversion.py
* Update examples/textual_inversion/textual_inversion.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* Update textual_inversion.py
* styling
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-02-16 15:39:51 +05:30
104afbce84
Standardize model card for textual inversion sdxl ( #6963 )
...
* standardize model card
* fix tags
* correct import styling and update tags
* run make style and make quality
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-02-16 14:27:11 +05:30
c0f5346a20
Fix procecss process ( #6591 )
...
* Fix words
* Fix
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-02-15 19:06:33 -10:00
087daee2f0
add: peft to the benchmark workflow ( #6989 )
2024-02-16 09:29:10 +05:30
7e164d98a8
Fix diffusers import prompt2prompt ( #6927 )
...
* Bugfix: correct import for diffusers
* Fix: Prompt2Prompt example
* Format style
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-02-15 15:30:16 -10:00
e6d1728e0a
[IP Adapters] feat: allow low_cpu_mem_usage in ip adapter loading ( #6946 )
...
* feat: allow low_cpu_mem_usage in ip adapter loading
* reduce the number of device placements.
* documentation.
* throw low_cpu_mem_usage warning only once from the main entry point.
2024-02-15 15:37:17 +05:30
8f2c7b4df0
[advanced sdxl lora script] - fix #6967 bug when using prior preservation loss ( #6968 )
...
* fix bug in micro-conditioning of class images
* fix bug in micro-conditioning of class images
* style
2024-02-15 12:20:05 +05:30
2e387dad5f
fix IPAdapter unload_ip_adapter test ( #6972 )
...
add
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2024-02-14 20:42:40 -10:00
9efe1e52c3
[docs] IP-Adapter ( #6897 )
...
* use cases
* first draft
* fix image links
* lcm-lora
* feedback
* review
* feedback
* feedback
2024-02-14 13:23:37 -08:00
37b09517b9
fix: controlnet inpaint single file. ( #6975 )
2024-02-14 19:04:57 +05:30
4343ce2c8e
[Core] Harmonize single file ckpt model loading ( #6971 )
...
* use load_model_into_meta in single file utils
* propagate to autoencoder and controlnet.
* correct class name access behaviour.
* remove torch_dtype from load_model_into_meta; seems unncessary
* remove incorrect kwarg
* style to avoid extra unnecessary line breaks
2024-02-14 10:49:06 +05:30
0ca7b68198
[PEFT / docs] Add a note about torch.compile ( #6864 )
...
* Update using_peft_for_inference.md
* add more explanation
2024-02-14 02:29:29 +01:00
3cf4f9c735
Allow passing config_file argument to ControlNetModel when using from_single_file ( #6959 )
...
* update
* update
* update
2024-02-13 18:54:53 +05:30
40dd9cb2bd
Move SDXL T2I Adapter lora test into PEFT workflow ( #6965 )
...
update
2024-02-13 17:08:53 +05:30
30bcda7de6
Fix flaky IP Adapter test ( #6960 )
...
update
2024-02-13 17:07:39 +05:30
9ea62d119a
[DPMSolverSinglestepScheduler] correct get_order_list for solver_order=2and lower_order_final=True ( #6953 )
...
* add
* change default
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
2024-02-12 22:10:33 -10:00
a326d61118
Fix configuring VAE from single file mixin ( #6950 )
...
* update
2024-02-12 22:10:05 -10:00
e7696e20f9
Updated lora inference instructions ( #6913 )
...
* Updated lora inference instructions
* Update examples/dreambooth/README.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* Update README.md
* Update README.md
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-02-13 09:35:20 +05:30
4b89aeffe1
[Type annotations] fixed in save_model_card ( #6948 )
...
fixed type annotations
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-02-13 08:56:45 +05:30
0a1daadef8
[docs] Community pipelines ( #6929 )
...
fix
2024-02-12 10:38:13 -08:00
Chong-U Lim