fix: dynamic SGM block mapping for SDXL kohya loras #4322
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Example: https://civitai.com/models/22279?modelVersionId=118556 |
|
The documentation is not available anymore as the PR was closed or merged. |
sayakpaul
approved these changes
Jul 27, 2023
patrickvonplaten
added a commit
that referenced
this pull request
Jul 28, 2023
* sdxl lora changes. * better name replacement. * better replacement. * debugging * debugging * debugging * debugging * debugging * remove print. * print state dict keys. * print * distingisuih better * debuggable. * fxi: tyests * fix: arg from training script. * access from class. * run style * debug * save intermediate * some simplifications for SDXL LoRA * styling * unet config is not needed in diffusers format. * fix: dynamic SGM block mapping for SDXL kohya loras (#4322) * Use lora compatible layers for linear proj_in/proj_out (#4323) * improve condition for using the sgm_diffusers mapping * informative comment. * load compatible keys and embedding layer maaping. * Get SDXL 1.0 example lora to load * simplify * specif ranks and hidden sizes. * better handling of k rank and hidden * debug * debug * debug * debug * debug * fix: alpha keys * add check for handling LoRAAttnAddedKVProcessor * sanity comment * modifications for text encoder SDXL * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * denugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * up * up * up * up * up * up * unneeded comments. * unneeded comments. * kwargs for the other attention processors. * kwargs for the other attention processors. * debugging * debugging * debugging * debugging * improve * debugging * debugging * more print * Fix alphas * debugging * debugging * debugging * debugging * debugging * debugging * clean up * clean up. * debugging * fix: text --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Batuhan Taskaya <batuhan@python.org>
sayakpaul
added a commit
that referenced
this pull request
Jul 28, 2023
* sdxl lora changes. * better name replacement. * better replacement. * debugging * debugging * debugging * debugging * debugging * remove print. * print state dict keys. * print * distingisuih better * debuggable. * fxi: tyests * fix: arg from training script. * access from class. * run style * debug * save intermediate * some simplifications for SDXL LoRA * styling * unet config is not needed in diffusers format. * fix: dynamic SGM block mapping for SDXL kohya loras (#4322) * Use lora compatible layers for linear proj_in/proj_out (#4323) * improve condition for using the sgm_diffusers mapping * informative comment. * load compatible keys and embedding layer maaping. * Get SDXL 1.0 example lora to load * simplify * specif ranks and hidden sizes. * better handling of k rank and hidden * debug * debug * debug * debug * debug * fix: alpha keys * add check for handling LoRAAttnAddedKVProcessor * sanity comment * modifications for text encoder SDXL * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * denugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * up * up * up * up * up * up * unneeded comments. * unneeded comments. * kwargs for the other attention processors. * kwargs for the other attention processors. * debugging * debugging * debugging * debugging * improve * debugging * debugging * more print * Fix alphas * debugging * debugging * debugging * debugging * debugging * debugging * clean up * clean up. * debugging * fix: text --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Batuhan Taskaya <batuhan@python.org>
orpatashnik
pushed a commit
to orpatashnik/diffusers
that referenced
this pull request
Aug 1, 2023
* sdxl lora changes. * better name replacement. * better replacement. * debugging * debugging * debugging * debugging * debugging * remove print. * print state dict keys. * print * distingisuih better * debuggable. * fxi: tyests * fix: arg from training script. * access from class. * run style * debug * save intermediate * some simplifications for SDXL LoRA * styling * unet config is not needed in diffusers format. * fix: dynamic SGM block mapping for SDXL kohya loras (huggingface#4322) * Use lora compatible layers for linear proj_in/proj_out (huggingface#4323) * improve condition for using the sgm_diffusers mapping * informative comment. * load compatible keys and embedding layer maaping. * Get SDXL 1.0 example lora to load * simplify * specif ranks and hidden sizes. * better handling of k rank and hidden * debug * debug * debug * debug * debug * fix: alpha keys * add check for handling LoRAAttnAddedKVProcessor * sanity comment * modifications for text encoder SDXL * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * denugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * up * up * up * up * up * up * unneeded comments. * unneeded comments. * kwargs for the other attention processors. * kwargs for the other attention processors. * debugging * debugging * debugging * debugging * improve * debugging * debugging * more print * Fix alphas * debugging * debugging * debugging * debugging * debugging * debugging * clean up * clean up. * debugging * fix: text --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Batuhan Taskaya <batuhan@python.org>
orpatashnik
pushed a commit
to orpatashnik/diffusers
that referenced
this pull request
Aug 1, 2023
* sdxl lora changes. * better name replacement. * better replacement. * debugging * debugging * debugging * debugging * debugging * remove print. * print state dict keys. * print * distingisuih better * debuggable. * fxi: tyests * fix: arg from training script. * access from class. * run style * debug * save intermediate * some simplifications for SDXL LoRA * styling * unet config is not needed in diffusers format. * fix: dynamic SGM block mapping for SDXL kohya loras (huggingface#4322) * Use lora compatible layers for linear proj_in/proj_out (huggingface#4323) * improve condition for using the sgm_diffusers mapping * informative comment. * load compatible keys and embedding layer maaping. * Get SDXL 1.0 example lora to load * simplify * specif ranks and hidden sizes. * better handling of k rank and hidden * debug * debug * debug * debug * debug * fix: alpha keys * add check for handling LoRAAttnAddedKVProcessor * sanity comment * modifications for text encoder SDXL * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * denugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * up * up * up * up * up * up * unneeded comments. * unneeded comments. * kwargs for the other attention processors. * kwargs for the other attention processors. * debugging * debugging * debugging * debugging * improve * debugging * debugging * more print * Fix alphas * debugging * debugging * debugging * debugging * debugging * debugging * clean up * clean up. * debugging * fix: text --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Batuhan Taskaya <batuhan@python.org>
orpatashnik
pushed a commit
to orpatashnik/diffusers
that referenced
this pull request
Aug 1, 2023
* sdxl lora changes. * better name replacement. * better replacement. * debugging * debugging * debugging * debugging * debugging * remove print. * print state dict keys. * print * distingisuih better * debuggable. * fxi: tyests * fix: arg from training script. * access from class. * run style * debug * save intermediate * some simplifications for SDXL LoRA * styling * unet config is not needed in diffusers format. * fix: dynamic SGM block mapping for SDXL kohya loras (huggingface#4322) * Use lora compatible layers for linear proj_in/proj_out (huggingface#4323) * improve condition for using the sgm_diffusers mapping * informative comment. * load compatible keys and embedding layer maaping. * Get SDXL 1.0 example lora to load * simplify * specif ranks and hidden sizes. * better handling of k rank and hidden * debug * debug * debug * debug * debug * fix: alpha keys * add check for handling LoRAAttnAddedKVProcessor * sanity comment * modifications for text encoder SDXL * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * denugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * up * up * up * up * up * up * unneeded comments. * unneeded comments. * kwargs for the other attention processors. * kwargs for the other attention processors. * debugging * debugging * debugging * debugging * improve * debugging * debugging * more print * Fix alphas * debugging * debugging * debugging * debugging * debugging * debugging * clean up * clean up. * debugging * fix: text --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Batuhan Taskaya <batuhan@python.org>
yoonseokjin
pushed a commit
to yoonseokjin/diffusers
that referenced
this pull request
Dec 25, 2023
* sdxl lora changes. * better name replacement. * better replacement. * debugging * debugging * debugging * debugging * debugging * remove print. * print state dict keys. * print * distingisuih better * debuggable. * fxi: tyests * fix: arg from training script. * access from class. * run style * debug * save intermediate * some simplifications for SDXL LoRA * styling * unet config is not needed in diffusers format. * fix: dynamic SGM block mapping for SDXL kohya loras (huggingface#4322) * Use lora compatible layers for linear proj_in/proj_out (huggingface#4323) * improve condition for using the sgm_diffusers mapping * informative comment. * load compatible keys and embedding layer maaping. * Get SDXL 1.0 example lora to load * simplify * specif ranks and hidden sizes. * better handling of k rank and hidden * debug * debug * debug * debug * debug * fix: alpha keys * add check for handling LoRAAttnAddedKVProcessor * sanity comment * modifications for text encoder SDXL * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * denugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * up * up * up * up * up * up * unneeded comments. * unneeded comments. * kwargs for the other attention processors. * kwargs for the other attention processors. * debugging * debugging * debugging * debugging * improve * debugging * debugging * more print * Fix alphas * debugging * debugging * debugging * debugging * debugging * debugging * clean up * clean up. * debugging * fix: text --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Batuhan Taskaya <batuhan@python.org>
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
* sdxl lora changes. * better name replacement. * better replacement. * debugging * debugging * debugging * debugging * debugging * remove print. * print state dict keys. * print * distingisuih better * debuggable. * fxi: tyests * fix: arg from training script. * access from class. * run style * debug * save intermediate * some simplifications for SDXL LoRA * styling * unet config is not needed in diffusers format. * fix: dynamic SGM block mapping for SDXL kohya loras (huggingface#4322) * Use lora compatible layers for linear proj_in/proj_out (huggingface#4323) * improve condition for using the sgm_diffusers mapping * informative comment. * load compatible keys and embedding layer maaping. * Get SDXL 1.0 example lora to load * simplify * specif ranks and hidden sizes. * better handling of k rank and hidden * debug * debug * debug * debug * debug * fix: alpha keys * add check for handling LoRAAttnAddedKVProcessor * sanity comment * modifications for text encoder SDXL * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * denugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * debugging * up * up * up * up * up * up * unneeded comments. * unneeded comments. * kwargs for the other attention processors. * kwargs for the other attention processors. * debugging * debugging * debugging * debugging * improve * debugging * debugging * more print * Fix alphas * debugging * debugging * debugging * debugging * debugging * debugging * clean up * clean up. * debugging * fix: text --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Batuhan Taskaya <batuhan@python.org>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Removes the assumption of fixed middle blocks (e.g. there are SDXL Kohya-SS style LoRAs with one middle layer). Also treats block ids as they are present in the state dict, not sequentially ordered keys. E.g. with a state dict that only modified input blocks 6, 8, 5, 4 the previous mapping treated them as if they were 0, 1, 2, 3.
Based on top of PR #4287