- 18 Jun, 2024 15 commits
-
-
Carolinabanana authored
Co-authored-by:
Sayak Paul <spsayakpaul@gmail.com> Co-authored-by:
YiYi Xu <yixu310@gmail.com>
-
Yongsen Mao authored
* add sd1.5 compatibility to controlnet-xs * set use_linear_projection by base_block * refine code style
-
kkj15dk authored
Making self.upsample actually be Upsample1D
-
Vasco Ramos authored
[SD3 Docs] Corrected title about loading model with T5 Corrected the documentation title to "Loading the single file checkpoint with T5" Previously, it incorrectly stated "Loading the single file checkpoint without T5" which contradicted the code snippet showing how to load the SD3 checkpoint with the T5 model
-
Gæros authored
* [LoRA] text encoder: read the ranks for all the attn modules * In addition to out_proj, read the ranks of adapters for q_proj, k_proj, and v_proj * Allow missing adapters (UNet already supports this) * ruff format loaders.lora * [LoRA] add tests for partial text encoders LoRAs * [LoRA] update test_simple_inference_with_partial_text_lora to be deterministic * [LoRA] comment justifying test_simple_inference_with_partial_text_lora * style --------- Co-authored-by: -
Andrew Hong authored
Co-authored-by: -
Sayak Paul authored
* shift factor argument to tiny * remove shift factor rejigging from the sd3 docs
-
Álvaro Somoza authored
* max_sequence_length for the T5 * updated img2img * apply suggestions --------- Co-authored-by:
-
Marc Sun authored
* Fix sharding when no device_map is passed * style * add tests * align * add docstring * format --------- Co-authored-by: -
MaoXianXin authored
-
Dhruv Nair authored
[Single File Loading] Handle unexpected keys in CLIP models when `accelerate` isn't installed. (#8462) * update * update * update * update * update --------- Co-authored-by:
-
Álvaro Somoza authored
* tased3 docs * apply suggestion --------- Co-authored-by: -
Sayak Paul authored
fix the position of param casting when loading them
-
Sayak Paul authored
refactor the density and weighting utilities.
-
Bagheera authored
Co-authored-by:
bghira <bghira@users.github.com> Co-authored-by:
Kashif Rasul <kashif.rasul@gmail.com>
-
- 17 Jun, 2024 4 commits
-
-
Álvaro Somoza authored
* initial commit * default back to 77 * better text * text correction --------- Co-authored-by: -
AmosDinh authored
Update controlnet.md Syntax error pipe -> pipeline
-
Dhruv Nair authored
temp pin numpy
-
YiYi Xu authored
* fix * up --------- Co-authored-by:yiyixuxu <yixu310@gmail,com>
-
- 16 Jun, 2024 3 commits
-
-
spacepxl authored
Fix the deletion of SD3 text encoders for Dreambooth/LoRA training if the text encoders are not being trained (#8536) * Update train_dreambooth_sd3.py to fix TE garbage collection * Update train_dreambooth_lora_sd3.py to fix TE garbage collection --------- Co-authored-by:
-
Rafie Walker authored
* Add lognorm and cosmap weighting * Implement mode sampling * Update examples/dreambooth/train_dreambooth_lora_sd3.py * Update examples/dreambooth/train_dreambooth_lora_sd3.py * Update examples/dreambooth/train_dreambooth_sd3.py * Update examples/dreambooth/train_dreambooth_sd3.py * Update examples/dreambooth/train_dreambooth_sd3.py * Update examples/dreambooth/train_dreambooth_lora_sd3.py * Update examples/dreambooth/train_dreambooth_sd3.py * Update examples/dreambooth/train_dreambooth_sd3.py * Update examples/dreambooth/train_dreambooth_lora_sd3.py * keep timestamp sampling fully on cpu --------- Co-authored-by:
-
Sayak Paul authored
* pin accelerate to 0.31.0 * update dep table * empty
-
- 14 Jun, 2024 1 commit
-
-
Jonathan Rahn authored
* add `sentencepiece` requirement for SD3 add `sentencepiece` requirement * Empty-Commit --------- Co-authored-by:
-
- 13 Jun, 2024 9 commits
-
-
Sayak Paul authored
thanks!
-
Tolga Cangöz authored
-
Sayak Paul authored
post release
-
Haofan Wang authored
-
YiYi Xu authored
remove prepare mask fn Co-authored-by:
-
Dhruv Nair authored
* update * update
-
Lucain authored
Fix PATH_IN_REPO in mirror workflow
-
ちくわぶ authored
* Fix duplicate variable assignments. * Fix duplicate variable assignments.
-
Beinsezii authored
-
- 12 Jun, 2024 8 commits
-
-
kkj15dk authored
Update scheduling_flow_match_euler_discrete.py Spelling: Foward -> Forward Co-authored-by: -
Beinsezii authored
-
Radamés Ajna authored
-
Sayak Paul authored
fix warning log
-
Sayak Paul authored
fix
-
Ameer Azam authored
becasue in Readme it was not correct train_dreambooth_sd3.py to train_dreambooth_lora_sd3
-
Dhruv Nair authored
* up * add sd3 * update * update * add tests * fix copies * fix docs * update * add dreambooth lora * add LoRA * update * update * update * update * import fix * update * Update src/diffusers/pipelines/stable_diffusion_3/pipeline_stable_diffusion_3.py Co-authored-by:
-
Jiwook Han authored
* translation about 3 documents into Korean * evaluation doc korean translation * _toctree.yml modify * doc title fix : philosopy->philosophy * Update docs/source/ko/conceptual/ethical_guidelines.md Co-authored-by:
Jihun Lim <31366038+heuristicwave@users.noreply.github.com> * Update docs/source/ko/conceptual/ethical_guidelines.md Co-authored-by:
Chulhwa (Evan) Han <cjfghk5697@ajou.ac.kr> * Update docs/source/ko/conceptual/evaluation.md Co-authored-by:
-
