lora训练之偷师 - 服务器托管|北京服务器租用|机房托管租用|IDC托管租用|机房机柜带宽租用-价格及费用咨询

自stable diffusion开源之后AIGC绘画方向定制化百花齐放百家争鸣。
而c站 https://civitai.com/

也聚集了全球爱好者的各种微调训练模型分享。

其中以lora为首，应用最广泛。

而这些模型是怎么训练出来的，细节到底是什么样的，没有多少人能说得清楚。

而就博主知道的，

使用最广泛的训练代码是这份 https://github.com/bmaltais/kohya_ss

它流行的原因主要是在其做了个GUI界面，便于很多不懂代码的人也能使用。

这里博主没打算讲解kohya_ss下具体训练方法和其参数。

想知道具体训练参数和细节，可以移步其wiki

https://github.com/bmaltais/kohya_ss/wiki/LoRA-training-parameters

还是不懂，也可以问各种gpt或者直接翻译成中文阅读即可。

现在主流最广泛使用的模型存储格式为 huggingface的safetensors

https://github.com/huggingface/safetensors

kohya_ss里默认会把训练参数填到safetensors的metadata里。

说到这里，lora训练之偷师答案呼之欲出。

假设我们从c站上把safetensors模型下载下来，

然后读出来它的metadata信息,

那不就能知道这个模型具体的训练参数吗？

而在博主实操读出来好几个主流模型的参数之后，很感慨:

c站上的模型真的很demo，训练的数据集大多都不大，分辨率也不高，有的也就百来张图。

训练参数也可以大概评估出来，每个模型作者的用心程度，

当然也可以作为评价模型的一种标准，

例如：看过了多少张图，什么样的分辨率训练的，训练了多久之类的。

也就对这个微调的模型能有个大概认知。

多看几个模型之后，

新手也可以快速上手训练自己的lora，定制自己的AI女友之类的。

你说你想直接抄他们的参数训练，当然也是可以的，偷师不可耻很光荣。

为了方便读取模型的模型的训练信息，博主写了个小工具。

开源地址为:

https://github.com/cpuimage/st_metadata_parser

使用也非常简单:

python st_metadata_parser.py input_file.safetensors

输出的参数具体含义可以参考：
https://github.com/bmaltais/kohya_ss/wiki/LoRA-training-parameters

附一份C站上某个lora模型文件的训练参数供一览：

[('ss_cache_latents', 'True'),
 ('ss_caption_dropout_every_n_epochs', '0'),
 ('ss_caption_dropout_rate', '0.0'),
 ('ss_caption_tag_dropout_rate', '0.0'),
 ('ss_clip_skip', '2'),
 ('ss_dataset_dirs', '{"rapunzel": {"n_repeats": 5, "img_count": 40}}'),
 ('ss_datasets',
  '[{"is_dreambooth": true, "batch_size_per_device": 2, "num_train_images": '
  '200, "num_reg_images": 0, "resolution": [512, 512], "enable_bucket": true, '
  '"min_bucket_reso": 256, "max_bucket_reso": 1024, "tag_frequency": '
  '{"rapunzel": {"rapunzel 1girl": 40, "solo": 39, "long hair": 37, "smile": '
  '26, "blonde hair": 38, "dress": 21, "very long hair": 18, "green eyes": 30, '
  '"crossed arms": 3, "corset": 5, "purple dress": 12, "breasts": 13, "open '
  'mouth": 7, "medium breasts": 5, "nipples": 7, "swimsuit": 2, "bikini": 1, '
  '"tongue": 2, "striped": 1, "lips": 7, "micro bikini": 1, "freckles": 5, '
  '"looking at viewer": 10, "long sleeves": 7, "cleavage": 3, "multiple boys": '
  '1, "puffy sleeves": 7, "2boys": 1, "full body": 4, "absurdly long hair": 2, '
  '"grin": 2, "hand on hip": 3, "juliet sleeves": 1, "blush": 3, "large '
  'breasts": 4, "hair ornament": 5, "standing": 2, "flower": 7, "cowboy shot": '
  '1, "teeth": 5, "indoors": 1, "hair flower": 5, "one-piece swimsuit": 1, '
  '"covered navel": 1, "makeup": 2, "cameltoe": 1, "highleg": 1, "lamp": 1, '
  '"braid": 4, "blurry": 2, "arm up": 1, "depth of field": 1, "blurry '
  'background": 2, "looking up": 3, "bokeh": 1, "upper body": 4, "short '
  'sleeves": 3, "closed eyes": 1, "small breasts": 1, "lying": 3, "signature": '
  '1, "on back": 1, "arms up": 2, "eyelashes": 1, "from above": 1, "happy": 1, '
  '"grass": 1, "cross-laced clothes": 1, "hair spread out": 1, "sitting": 4, '
  '"outdoors": 2, "barefoot": 7, "water": 1, "tree": 2, "pink dress": 1, '
  '"holding flower": 1, "lily pad": 1, "simple background": 5, "white '
  'background": 3, "frog": 4, "black background": 2, "child": 1, "star print": '
  '1, "lantern": 1, "blue eyes": 2, "navel": 5, "underwear": 2, "panties": 2, '
  '"thigh gap": 1, "bound": 2, "bdsm": 2, "bondage": 2, "gag": 1, "gagged": 1, '
  '"improvised gag": 1, "cloth gag": 1, "nude": 5, "tongue out": 1, "saliva": '
  '1, "arms behind back": 1, "seiza": 1, "bound arms": 1, "on head": 1, '
  '"animal on head": 1, "holding hair": 1, "tiara": 1, "crown": 1, "princess": '
  '1, "hands on own head": 1, "mirror": 2, "frying pan": 2, "nature": 1, '
  '"parted lips": 1, "blue background": 1, "shirt": 1, "choker": 2, "huge '
  'breasts": 1, "colored skin": 1, "bursting breasts": 1, "thighhighs": 2, '
  '"jewelry": 1, "thighs": 1, "earrings": 1, "pussy": 3, "spread legs": 2, '
  '"cum": 1, "high heels": 1, "kneeling": 1, "uncensored": 3, "cum in pussy": '
  '1, "phone": 1, "cellphone": 1, "smartphone": 1, "after sex": 1, "holding '
  'phone": 1, "cumdrip": 1, "brown thighhighs": 1, "gloves": 1, "multicolored '
  'hair": 1, "white gloves": 1, "topless": 1, "pink panties": 1, "fishnet '
  'thighhighs": 1, "ass": 1, "feet": 1, "soles": 1, "on stomach": 1, "the '
  'pose": 1, "nail polish": 1, "tan": 1, "personification": 1, "tanlines": 1, '
  '"detached sleeves": 1, "armpits": 1, "pillow": 1}}, "bucket_info": '
  '{"buckets": {"0": {"resolution": [320, 704], "count": 30}, "1": '
  '{"resolution": [384, 640], "count": 95}, "2": {"resolution": [448, 576], '
  '"count": 50}, "3": {"resolution": [512, 512], "count": 20}, "4": '
  '{"resolution": [576, 448], "count": 5}}, "mean_img_ar_error": '
  '0.042025975009129204}, "subsets": [{"img_count": 40, "num_repeats": 5, '
  '"color_aug": false, "flip_aug": false, "random_crop": false, '
  '"shuffle_caption": true, "keep_tokens": 1, "image_dir": "rapunzel", '
  '"class_tokens": null, "is_reg": false}]}]'),
 ('ss_epoch', '10'),
 ('ss_face_crop_aug_range', 'None'),
 ('ss_full_fp16', 'False'),
 ('ss_gradient_accumulation_steps', '1'),
 ('ss_gradient_checkpointing', 'False'),
 ('ss_learning_rate', '0.0005'),
 ('ss_lowram', 'True'),
 ('ss_lr_scheduler', 'cosine_with_restarts'),
 ('ss_lr_warmup_steps', '50'),
 ('ss_max_grad_norm', '1.0'),
 ('ss_max_token_length', '225'),
 ('ss_max_train_steps', '1010'),
 ('ss_min_snr_gamma', '5.0'),
 ('ss_mixed_precision', 'fp16'),
 ('ss_multires_noise_discount', '0.3'),
 ('ss_multires_noise_iterations', 'None'),
 ('ss_network_alpha', '16'),
 ('ss_network_dim', '32'),
 ('ss_network_module', 'networks.lora'),
 ('ss_new_sd_model_hash',
  'b0c91a8a93ab63b8b513046c2e2181a4ce78b83367ee7e26354ba9e018ea102f'),
 ('ss_noise_offset', 'None'),
 ('ss_num_batches_per_epoch', '101'),
 ('ss_num_epochs', '10'),
 ('ss_num_reg_images', '0'),
 ('ss_num_train_images', '200'),
 ('ss_optimizer', 'bitsandbytes.optim.adamw.AdamW8bit'),
 ('ss_output_name', 'rapunzel'),
 ('ss_prior_loss_weight', '1.0'),
 ('ss_sd_model_hash', '66f58dbb'),
 ('ss_sd_model_name', 'fp16-pruned.ckpt'),
 ('ss_sd_scripts_commit_hash', 'e6ad3cbc66130fdc3bf9ecd1e0272969b1d613f7'),
 ('ss_seed', '42'),
 ('ss_session_id', '1637709685'),
 ('ss_steps', '1010'),
 ('ss_tag_frequency',
  '{"rapunzel": {"rapunzel 1girl": 40, "solo": 39, "long hair": 37, "smile": '
  '26, "blonde hair": 38, "dress": 21, "very long hair": 18, "green eyes": 30, '
  '"crossed arms": 3, "corset": 5, "purple dress": 12, "breasts": 13, "open '
  'mouth": 7, "medium breasts": 5, "nipples": 7, "swimsuit": 2, "bikini": 1, '
  '"tongue": 2, "striped": 1, "lips": 7, "micro bikini": 1, "freckles": 5, '
  '"looking at viewer": 10, "long sleeves": 7, "cleavage": 3, "multiple boys": '
  '1, "puffy sleeves": 7, "2boys": 1, "full body": 4, "absurdly long hair": 2, '
  '"grin": 2, "hand on hip": 3, "juliet sleeves": 1, "blush": 3, "large '
  'breasts": 4, "hair ornament": 5, "standing": 2, "flower": 7, "cowboy shot": '
  '1, "teeth": 5, "indoors": 1, "hair flower": 5, "one-piece swimsuit": 1, '
  '"covered navel": 1, "makeup": 2, "cameltoe": 1, "highleg": 1, "lamp": 1, '
  '"braid": 4, "blurry": 2, "arm up": 1, "depth of field": 1, "blurry '
  'background": 2, "looking up": 3, "bokeh": 1, "upper bo服务器托管网dy": 4, "short '
  'sleeves": 3, "closed eyes": 1, "small breasts": 1, "lying": 3, "signature": '
  '1, "on back": 1, "arms up": 2, "eyelashes": 1, "from above": 1, "happy": 1, '
  '"grass": 1, "cross-laced clothes": 1, "hair spread out": 1, "sitting": 4, '
  '"outdoors": 2, "barefoot": 7, "water": 1, "tree": 2, "pink dress": 1, '
  '"holding flower": 1, "lily pad": 1, "simple background": 5, "white '
  'background": 3, "frog": 4, "black background": 2, "child": 1, "star print": '
  '1, "lantern": 1, "blue eyes": 2, "navel": 5, "underwear": 2, "panties": 2, '
  '"thigh gap": 1, "bound": 2, "bdsm": 2, "bondage": 2, "gag": 1, "gagged": 1, '
  '"improvised gag": 1, "cloth gag": 1, "nude": 5, "tongue out": 1, "saliva": '
  '1, "arms behind back": 1, "seiza": 1, "bound arms": 1, "on head": 1, '
  '"animal on head": 1, "holding hair": 1, "tiara": 1, "crown": 1, "princess": '
  '1, "hands on own head": 1, "mirror": 2, "frying pan": 2, "nature": 1, '
  '"parted lips": 1, "blue background": 1, "shirt": 1, "choker": 2, "huge '
  'breasts": 1, "colored skin": 1, "bursting breasts": 1, "thighhighs": 2, '
  '"jewelry": 1, "thighs": 1, "earrings": 1, "pussy": 3, "spread legs": 2, '
  '"cum": 1, "high heels": 1, "kneeling": 1, "uncensored": 3, "cum in pussy": '
  '1, "phone": 1, "cellphone": 1, "smartphone": 1, "after sex": 1, "holding '
  'phone": 1, "cumdrip": 1, "brown thighhighs": 1, "gloves": 1, "multicolored '
  'hair": 1, "white gloves": 1, "topless": 1, "pink panties": 1, "fishnet '
  'thighhighs": 1, "ass": 1, "feet": 1, "soles": 1, "on stomach": 1, "the '
  'pose": 1, "nail polish": 1, "tan": 1, "personification": 1, "tanlines": 1, '
  '"detached sleeves": 1, "armpits": 1, "pillow": 1}}'),
 ('ss_text_encoder_lr', '0.0001'),
 ('ss_training_comment', 'None'),
 ('ss_training_finished_at', '1694906008.5775223'),
 ('ss_training_started_at', '1694905352.3001792'),
 ('ss_unet_lr', '0.0005'),
 ('ss_v2', 'False'),
 ('sshs_legacy_hash', 'fd5d0c6f'),
 ('sshs_model_hash',
  '0f9a9c96e707b34f1591ed9d24e788769cb72e2040f380aa7c31b6a49ca783b2')]

有数据就比较直观，不然这篇博文，就显得干巴巴的。

也算为业界做了一点点贡献。

提一个额外的话题，

由于diffusers和stable-diffusion-webui的实现十分臃肿，
并且屎山越来越大，非常不便于研发以及学习。
为了远离那堆玩意，博主化身屎壳郎，花了不少精力对stable diffusion进行了整理和重写。
开源了sd 1.5和 sdxl 1.0 两个仓库，主要以keras/TensorFlow为主，兼容pytroch的模型权重。
项目地址为:
sd1.5:
https://github.com/cpuimage/minSDTF
sdxl 1.0：
https://github.com/cpuimage/minSDXLTF
目前有空会持续更新，目标是把webui的主要功能以比较简洁优雅的方式实现，路漫漫其修远兮。
如果有小伙伴有能力也想加入，欢迎联系博主，一起摇摆。

也有业内好友期望博主写一份keras/tensorflow版本的lora训练框架，只能说有时间的话，会写的。

最后唠叨几句，kohya_ss训练框架的作者，其代码好几个地方逻辑写错了，小伙伴们要注意了。

最后的最后，

有stable diffusion相关的训练或者开发定制，不论是需求还是各种问题都可以通过以下方式联系博主，

微信: Dbgmonks

QQ: 200759103

邮箱: gaozhihan@vip.qq.com

注: 博主提供有偿服务, 不注明来意者一律拒绝。

TRANSLATE with x

English

TRANSLATE with

COPY THE URL BELOW

Back

EMBED THE SNIPPET BELOW IN YOUR SITE

Enable collaborative features and customize 服务器托管网widget: Bing Webmaster Portal

Back

This page is in English

Translate to Simplified Chinese

Afrikaans
Albanian
Amharic
Arabic
Armenian
Azerbaijani
Bengali
Bulgarian
Catalan
Croatian
Czech
Danish
Dutch
English
Estonian
Finnish
French
German
Greek
Gujarati
Haitian Creole
Hebrew
Hindi
Hungarian
Icelandic
Indonesian
Italian
Japanese
Kannada
Kazakh
Khmer
Korean
Kurdish (Kurmanji)
Lao
Latvian
Lithuanian
Malagasy
Malay
Malayalam
Maltese
Maori
Marathi
Myanmar (Burmese)
Nepali
Norwegian
Pashto
Persian
Polish
Portuguese
Punjabi
Romanian
Russian
Samoan
Simplified Chinese
Slovak
Slovenian
Spanish
Swedish
Tamil
Telugu
Thai
Traditional Chinese
Turkish
Ukrainian
Urdu
Vietnamese
Welsh

Always translate English to Simplified ChinesePRO
Never translate English
Never translate i.cnblogs.com

服务器托管，北京服务器托管，服务器租用 http://www.fwqtg.net
机房租用，北京机房租用，IDC机房托管， http://www.fwqtg.net

相关推荐: shell命令概述 Shell作用：命令解释器介于操作系统内核与用户之间，负责解释命令行获得命令帮助内部命令help 命令的“–help” 选项使用man命令阅读手册页命令行编辑的几个辅助

shell命令概述 Shell作用：命令解释器介于操作系统内核与用户之间，负责解释命令行获得命令帮助内部命令help 命令的“–help” 选项使用man命令阅读手册页命令行编辑的几个辅助操作 Tab键：自动补齐反斜杠“”：强制换行快捷键 Ct…

Arabic	Hebrew	Polish
Bulgarian	Hindi	Portuguese
Catalan	Hmong Daw	Romanian
Chinese Simplified	Hungarian	Russian
Chinese Traditional	Indonesian	Slovak
Czech	Italian	Slovenian
Danish	Japanese	Spanish
Dutch	Klingon	Swedish
English	Korean	Thai
Estonian	Latvian	Turkish
Finnish	Lithuanian	Ukrainian
French	Malay	Urdu
German	Maltese	Vietnamese
Greek	Norwegian	Welsh
Haitian Creole	Persian

服务器托管，北京服务器托管，服务器租用，机房机柜带宽租用