Issues
- 2
Add AuraFlow support
#1440 opened by StableLlama - 37
Support FLUX series models
#1445 opened by ddpasa - 3
- 1
What is the argument for loading existing lora weight?
#1448 opened by TeKett - 1
train_README-ja 誤表記/ train_README-ja Typo
#1446 opened by FA7770 - 2
Pony model fusion lora error
#1442 opened by qqyt110 - 0
Parse safetensors files into a JSON configuration file
#1444 opened by Shyryp - 4
Is get_crop_ltrb working correctly?
#1443 opened by yhzx233 - 1
Is class_tokens used when captions are provided
#1441 opened by FurkanGozukara - 0
- 25
Training on 2x H100 on Ubuntu and speed is same as 1x H100 what we are doing wrong?
#1434 opened by FurkanGozukara - 0
SD3.0 Extract lora feature?
#1438 opened by DarkViewAI - 0
weighted captions for SDXL
#1437 opened by clementine-of-whitewind - 0
- 5
- 0
- 4
- 6
SD3 training error
#1418 opened by GoofyAi - 6
MultipleInvalid: extra keys not allowed @ data['datasets'][0]['subsets'][1]['is_reg']
#1428 opened by voplica-git - 2
[Bugs] bad quality in ARB resize
#1430 opened by KohakuBlueleaf - 1
improve ?
#1423 opened by SYBSYBFUFU00005 - 0
SDXL Lora text encoder training question
#1425 opened by DarkViewAI - 0
Cache latents takes years
#1424 opened by OliviaOliveiira - 1
Given groups=1, weight of size [1536, 16, 2, 2], expected input[4, 4, 128, 96] to have 16 channels, but got 4 channels instead
#1419 opened by hieusttruyen - 1
[Feature request]: Add Kolors Support
#1415 opened by maybleMyers - 9
SD3 intel_pytorch_extension problem
#1421 opened by OliviaOliveiira - 1
SDXL training crashes when trying to use fp16 and model is not defined as variant model
#1420 opened by omgold - 2
KeyError: 'time_embed.0.weight while Training on SD3.
#1414 opened by vsatyamesc - 1
LoKr Error when training Lora
#1402 opened by Verun11 - 6
sd3 train,loss is nan
#1407 opened by chongxian - 0
sd3 training supports text encoder
#1410 opened by mliand - 3
- 17
[Feature Request] Add new way to manage timestep distribution and new loss offset feature
#1375 opened by Anzhc - 30
- 0
Training a LoRA model on Kohya ss - issue
#1411 opened by nounou99jiji - 4
SD3 training error
#1389 opened by paoloski97 - 0
- 4
训练488万张图片时中间突然出现OS.ERROR
#1385 opened by 2575044704 - 0
sd3 train supports text encoder training
#1403 opened by mliand - 0
Would it be possible to add BREAK to training?
#1398 opened by TeKett - 2
- 0
Caption dropout at high noise
#1400 opened by ddpasa - 0
tag_images_by_wd14_tagger.py +sd3 Game Changer Ideas
#1399 opened by ao899 - 6
is the sd3_minimal_inference something wrong?
#1388 opened by lzran - 3
Large datasets produce corrupt LoRAs
#1380 opened by Yo1up - 3
SD3 Training problem
#1382 opened by leonary - 0
How about sd3 lora trainning?
#1386 opened by zengjie617789 - 0
Installation problem
#1384 opened by alex13by - 0
输出模型时将全部文件输出
#1379 opened by 1030zero - 0
Google Colab - from_pretrained hang
#1377 opened by asutermo