kohya-ss/sd-scripts issues and pull requests

#1648 - Support Sdxl Controlnet

Pull Request - State: closed - Opened by sdbds 4 months ago - 1 comment

#1647 - cant sample with flux (fine-tuning)

Issue - State: closed - Opened by betterftr 4 months ago - 4 comments

#1646 - Fix CNet training for sd1 (and maybe 2)

Pull Request - State: closed - Opened by elthariel 4 months ago - 2 comments

#1645 - Dataset maker sd1.5 - wd-tagger module stopped working on colab

Issue - State: open - Opened by nevo993 4 months ago

#1644 - Please add AdEMAMix to the scripts.

Issue - State: closed - Opened by DarkAlchy 4 months ago - 2 comments

#1643 - Regarding the Multi-Level Caption

Issue - State: open - Opened by sdbds 4 months ago - 3 comments

#1642 - about flux image normalization

Issue - State: closed - Opened by Jimzhou82sub 4 months ago - 2 comments

#1641 - Kohya_ss native trainer colab broken yesterday. Captured before/ after install log. Jax, Key array.

Issue - State: open - Opened by SarahPeterson2854 4 months ago - 10 comments

#1640 - New optimizer:AdEMAMix8bit and PagedAdEMAMix8bit

Pull Request - State: closed - Opened by sdbds 4 months ago - 9 comments

#1638 - Was "Validation Loss" ever successfully implemented?

Issue - State: open - Opened by mostlyhuman 5 months ago

#1637 - Update train_network_README-zh.md

Pull Request - State: open - Opened by a67793581 5 months ago

#1636 - Specify blocks to Train w/ Finetuning?

Issue - State: open - Opened by setothegreat 5 months ago - 3 comments

#1635 - Drop text encoder weights

Issue - State: closed - Opened by oovm 5 months ago - 1 comment

#1634 - FLUX LoRA Training - Text Encoder active training indicated when it should be disabled with --network_train_unet_only

Issue - State: open - Opened by Enyakk 5 months ago - 2 comments

#1633 - FLUX: Bleeding?

Issue - State: closed - Opened by DarkAlchy 5 months ago - 5 comments

#1632 - fix import and make npz for alpha_mask

Pull Request - State: closed - Opened by Maru-mee 5 months ago - 17 comments

#1631 - Recommended settings for ScheduleFree.

Issue - State: closed - Opened by waomodder 5 months ago - 4 comments

#1630 - Issue Reminder

Issue - State: open - Opened by lynrayy 5 months ago

#1629 - Extract Flux Lora not working after 93/304

Issue - State: closed - Opened by DarkViewAI 5 months ago

#1628 - Make timesteps work in the standard way when Huber loss is used

Pull Request - State: closed - Opened by recris 5 months ago - 6 comments

#1627 - When I train with multiple GPUs, this error will be reported. This has been bothering me for a long time. How can I solve it

Issue - State: closed - Opened by jinwei1660 5 months ago - 1 comment

#1626 - how to use flux full-finetune safetensors in diffusers?

Issue - State: open - Opened by neuron-party 5 months ago - 3 comments

#1624 - Strange behavior with --network_args parameter

Issue - State: open - Opened by codecomputation 5 months ago

#1623 - neither 'setup.py' nor 'pyproject.toml' found.

Issue - State: closed - Opened by wzgrx 5 months ago

#1622 - Inverted extraction for FLUX.

Issue - State: closed - Opened by DarkAlchy 5 months ago - 4 comments

#1621 - lora to original flux lora

Issue - State: closed - Opened by LixDemon 5 months ago - 1 comment

#1620 - fix: backward compatibility for text_encoder_lr

Pull Request - State: closed - Opened by Akegarasu 5 months ago - 1 comment

#1619 - Retain alpha in `pil_resize` for `--alpha_mask`

Pull Request - State: closed - Opened by emcmanus 5 months ago - 4 comments

#1618 - TypeError: get_cosine_schedule_with_warmup() got an unexpected keyword argument 'num_decay_steps'

Issue - State: closed - Opened by AndreR 5 months ago - 6 comments

#1617 - AttributeError: 'LycorisNetworkKohya' object has no attribute 'train_t5xxl'

Issue - State: closed - Opened by sd2530615 5 months ago - 4 comments

#1616 - ValueError: invalid literal for int() with base 10: 'still' when using facecrop

Issue - State: closed - Opened by Seedmanc 5 months ago - 1 comment

#1615 - Bug fix: alpha_mask load

Pull Request - State: closed - Opened by Maru-mee 5 months ago - 5 comments

#1614 - Issue for convert_flux_lora.py: RuntimeError: Some tensors share memory...

Issue - State: closed - Opened by terrificdm 5 months ago - 5 comments

#1613 - [Feature Request] Decouple `linear1` and `linear2` Flux layers in network_args

Issue - State: open - Opened by EricBCoding 5 months ago - 8 comments

#1612 - Flux merge tool does not properly handle LoRA keys from AI-Toolkit when merging w/ Flux.dev model - All keys "Unused" / Unchanged model file outputted

Issue - State: open - Opened by CCpt5 5 months ago - 9 comments

#1611 - Does the FLUX/SD3 branch not work with SDXL yet?

Issue - State: closed - Opened by DarkAlchy 5 months ago

#1610 - FLUX LoRA Extraction Resemblance Issue

Issue - State: closed - Opened by FurkanGozukara 5 months ago - 1 comment

#1609 - Either "cuDNN SDPA backward got grad_output.strides() != output.strides()" or OutOfMemory

Issue - State: closed - Opened by Tablaski 5 months ago - 5 comments

#1608 - Flux does not support Prodigy?

Issue - State: closed - Opened by DarkAlchy 5 months ago - 2 comments

#1607 - Flux fine-tune text encoder rate is too high; need to be able to set separately

Issue - State: open - Opened by BelieveDiffusion 5 months ago - 2 comments

#1606 - Update submodules as well since MPS changes were needed

Pull Request - State: open - Opened by JoeyOverby 5 months ago

#1605 - sd3 schedule free opt

Pull Request - State: closed - Opened by kohya-ss 5 months ago - 6 comments
Labels: help wanted

#1603 - flux lora training does not start,error: returned non-zero exit status 1

Issue - State: closed - Opened by zxf5843029 5 months ago - 4 comments

#1602 - unexpected keyword argument 'num_decay_steps' when using cosine or linear scheduler (sd3 branch)

Issue - State: closed - Opened by Enyakk 5 months ago - 1 comment

#1601 - poolFD failed error when caching latents for flux finetuning

Issue - State: open - Opened by huxian0402 5 months ago - 4 comments

#1600 - New ScheduleFree support for Flux

Pull Request - State: closed - Opened by sdbds 5 months ago - 2 comments

#1599 - 上手く学習が完了しません

Issue - State: closed - Opened by bell123405 5 months ago - 4 comments

#1598 - flux with flow matching schedule

Issue - State: closed - Opened by Jimzhou82sub 5 months ago

#1597 - Error loading fbgemm.dll

Issue - State: open - Opened by AndreR 5 months ago - 1 comment

#1596 - How to convert a safetensors(finetuned sdxl model) to diffusers dir format?

Issue - State: open - Opened by laolongboy 5 months ago

#1595 - FLUX training for 8GB VRAM?

Issue - State: open - Opened by cocktailpeanut 5 months ago - 14 comments

#1594 - What does split_mode actually do?

Issue - State: closed - Opened by WainWong 5 months ago - 2 comments

#1592 - Critical typo fix

Pull Request - State: closed - Opened by cocktailpeanut 5 months ago

#1591 - error when use deepspeed for FLUX.1 fine-tuning

Issue - State: open - Opened by huxian0402 5 months ago - 5 comments

#1590 - What fp8_base does？

Issue - State: closed - Opened by WainWong 5 months ago - 1 comment

#1589 - flux lora training does not start

Issue - State: open - Opened by nim00e 5 months ago - 3 comments

#1588 - Flux textual_inversion

Issue - State: open - Opened by aiXander 5 months ago - 16 comments

#1587 - flux full fine-tuning output bad result

Issue - State: closed - Opened by huxian0402 5 months ago - 3 comments

#1586 - (sd3-Flux_LoRA) training stuck

Issue - State: closed - Opened by pranauv1 5 months ago - 8 comments

#1585 - Unused keys when merge flux-dev with hyper-sd lora

Issue - State: closed - Opened by huxian0402 5 months ago - 1 comment

#1584 - *Possible important fixes for some issues with flux

Issue - State: open - Opened by DriveHabits 5 months ago

#1583 - [Feature request] --caption_dropout_rate when cache te output

Issue - State: open - Opened by gesen2egee 5 months ago
Labels: enhancement

#1582 - Can not load in ComfyUI and --network_args "split_qkv=True" does not work

Issue - State: open - Opened by JohnsonXi 5 months ago - 2 comments

#1581 - flux lora training issue

Issue - State: open - Opened by wanglaofei 5 months ago - 1 comment

#1580 - Support : OFT merge to base model

Pull Request - State: closed - Opened by Maru-mee 5 months ago - 14 comments

#1579 - why my flux dreambooth version can't inference right image but a noise Map

Issue - State: open - Opened by godwenbin 5 months ago - 2 comments

#1578 - Multi-GPU training sample generation problem - FLUX

Issue - State: open - Opened by FurkanGozukara 5 months ago

#1577 - Random crashes: 'NoneType' object has no attribute 'ndim'

Issue - State: open - Opened by sampbarrow 5 months ago

#1576 - Improve wandb logging

Pull Request - State: closed - Opened by p1atdev 5 months ago - 2 comments

#1575 - Support Lora Block Weight (LBW) to svd_merge_lora.py

Pull Request - State: closed - Opened by terracottahaniwa 5 months ago - 33 comments

#1574 - About sdxl_merge_lora.py using GPU for merging

Issue - State: open - Opened by qqyt110 5 months ago - 1 comment

#1573 - Create init.py in networks folder

Pull Request - State: open - Opened by Leommm-byte 5 months ago

#1572 - Flux Lora producing blurry images

Issue - State: open - Opened by nitinh12 5 months ago - 19 comments

#1571 - Flux.1 LoRA training issue

Issue - State: closed - Opened by paoloski97 5 months ago - 13 comments

#1570 - Possible additon of quantization or Nfloat4 for lower vram (Same quality as fp8/bf16)

Issue - State: open - Opened by DriveHabits 5 months ago - 3 comments
Labels: enhancement

#1569 - Flux Image Logging to wandb is Lost in Multi-GPU Mode

Issue - State: open - Opened by tristanwqy 5 months ago - 1 comment
Labels: bug

#1568 - How do I create this JSON file in flux training? Is there an example file?

Issue - State: closed - Opened by pzzmyc 5 months ago

#1567 - Flux Lora Resize takes 25mins and also does not resize at the end

Issue - State: closed - Opened by DarkViewAI 5 months ago

#1566 - Flux Schnell lora size is too small (1.42 MB) and Does not generate images of the character that it was trained on.

Issue - State: open - Opened by Hassan-jr 5 months ago - 3 comments
Labels: enhancement

#1565 - Merge Flux all in one

Issue - State: open - Opened by oovm 5 months ago - 2 comments

#1564 - Flux shift method update

Pull Request - State: open - Opened by sdbds 5 months ago - 3 comments
Labels: help wanted

#1563 - negative number for iteration per second

Issue - State: closed - Opened by alexcong 5 months ago - 2 comments

#1562 - Flux: RuntimeError: Input type (float) and bias type (c10::BFloat16) should be the same

Issue - State: closed - Opened by sampbarrow 5 months ago - 2 comments

#1561 - RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'

Issue - State: closed - Opened by bulolsi 5 months ago - 2 comments

#1560 - CUDA Out of Memory on Flux Minimal Inference code.

Issue - State: closed - Opened by mazharosama 5 months ago - 2 comments

#1559 - How to Properly Resume Training w/ Respect to Schedulers?

Issue - State: open - Opened by setothegreat 5 months ago - 10 comments

#1558 - how is multi gpu loss gathered?

Issue - State: open - Opened by SnapixAI 5 months ago - 1 comment

#1557 - torch not found error

Issue - State: closed - Opened by PheonixAi420 5 months ago - 7 comments

#1556 - FLUX LoRA training getting terminated without any error - 64 GB RAM - video shared

Issue - State: closed - Opened by FurkanGozukara 5 months ago - 11 comments

#1555 - Compatibility of Flux Pruned fp8 Model with sd-scripts for Fine-tuning

Issue - State: closed - Opened by blackmagic24 5 months ago

#1554 - torch 2.3.1+cuda12.1 with flux lora train, but got the train error when use single GPU, pls help

Issue - State: open - Opened by lilyzlt 5 months ago - 1 comment

#1553 - Using FP8 mixed-precision in accelerate give error. Where and how do I install the necessary packages?

Issue - State: open - Opened by Signorlimone 5 months ago - 4 comments

#1551 - Running Flux Lora training on 2 GPUs

Issue - State: open - Opened by innokean 5 months ago - 11 comments

#1550 - Bump crate-ci/typos from 1.19.0 to 1.24.3

Pull Request - State: closed - Opened by dependabot[bot] 5 months ago
Labels: dependencies, github_actions

GitHub / kohya-ss/sd-scripts issues and pull requests