TR写实realistic-SD2.1

CHECKPOINT
Original


Updated:

341

This model is about REALISTIC    .                                                                                                         

Recommended resolution :W640 x H960

推荐分辨率:W640 x H960

Iteration steps; 20+

Sampling method; Euler a,DIMM,Euler,restart

High resolution fix: enable - Latent 2X

Redraw width: 0.5

Use vae-ft-mse-840000-ema

NOTICE

I don't force you to download this model.

Don't write a review unless it's a review that supports and loves me.

If it doesn't fit my model and policy, don't come to me anymore.

Your 5 star and likes are very helpful to me.

Have a nice day.

这个模型是关于写实风格。

建议分辨率 :Width640xHeight960

迭代步骤; 20+

采样方法; 推荐使用Euler,restart作为采样器。

高分辨率修复:enable - Latent 2X

重绘宽度: 0.5

使用 vae-ft-mse-840000-ema
Use Restrictions:

You agree not to use the Model or Derivatives of the Model:

- In any way that violates any applicable national, federal, state, local or international law or regulation

- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way

- To generate or disseminate verifiably false information and/or content with the purpose of harming others

- To generate or disseminate personal identifiable information that can be used to harm an individual

- To defame, disparage or otherwise harass others

- For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation

- For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics

- To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm

- For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories

- To provide medical advice and medical results interpretation

- To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use)

模型使用条款

(1)使用本模型即表示用户已同意本法规的所有条款。

(2)本模型仅限于个人使用,不得用于任何商业化的目的。

(3)用户不得将本模型用于任何非法或有害的目的,包括但不限于侵犯他人权益、传播虚假信息、扰乱社会秩序等。

(4)用户应仅以自己的名义使用本模型,不得将其用于任何非法或有害的目的。

(5)用户应遵守所有适用的法律法规,包括但不限于网络安全、数据保护、不正当竞争、消费者保护等领域的法律或法规。

(6)用户应尊重他人的合法权益,不得侵犯任何第三方的权益。

(7)如因使用本模型而引起的任何纠纷或诉讼,用户应自行承担相应的法律责任。

(8)用户应在使用本模型时,采取必要的技术和管理措施,确保数据的安全性和保密性。

(9)用户应在使用本模型时,遵守知识产权法的规定,不得侵犯任何第三方的知识产权。

(10)不得将本模型用于任何非法或有害的目的,包括但不限于侵犯他人权益、传播虚假信息、扰乱社会秩序等。

(11)不得使用本模型以任何方式剥削、伤害或试图剥削或伤害未成年人为目的,包括但不限于任何涉及未成年人的内容、活动或服务。

(12)不得使用本模型生成或传播可验证的虚假信息或内容,或个人身份信息,以伤害他人为目的。

(13)不得使用本模型诽谤、诋毁或以其他方式骚扰他人。

(14)不得使用本模型进行全自动决策,从而对个人的合法权利产生不利影响,或制定具有约束力和可强制执行的法律义务。

(15)不得使用本模型进行任何旨在或具有歧视性或伤害个人或群体的行为,包括基于在线或离线社交行为或已知或预测的个人或人格特征的行为。

(16)不得使用本模型来利用特定人群的任何弱点,基于年龄、社会地位、身体或精神特征,以扭曲该人群中与该特定人群相关的行为,从而造成或可能造成该人或其他人的身体或心理伤害。

(17)不得使用本模型进行任何旨在或具有歧视性或伤害个人或群体的行为,基于受法律保护的特征或类别。

(18)本模型不得用于提供医疗咨询或解释医学结果。

(19)不得使用本模型生成或传播信息,用于司法管理、执法、移民或庇护程序,例如通过文本分析预测个人犯罪行为。

Version Detail

SD 2.1 768
The second to last maintenance is too difficult to refine, and there are few market derivatives embedded with VAE, which is too costly and cannot be used to generate power for love. A model without equipment estimates several thousand, and 1 girl cannot go straight without a full body. Realistic: 1, solo, female, female, and 1 girl can achieve card drawing Hanfu Qipao (dress) Cos (cosplay clothes) Robot Other categories etc. CFGScale: 2-5: The first four images correspond to CFG; 2, 3, 4, 5. This version is the SD-2.1-768 base model. This bar model no longer supports parallel light realistic forward prompts for SD1.5. It is recommended to provide more facial details and not support 1-girl straight out, similar to sdxl, which is better. But try to use words or short sentences. There seems to be a difference in the guidance of online mapping for CFG among different websites, which can be confirmed by oneself. Generally speaking, it is 1-7, but the style and presentation situation are different———————————————————————————————————————— Example positive cue words: realistic, nsfw: 2, detailed face, 1Girl, solo, long hair, Jewelry neck lace, earrings, Jewelry, complexdetails, 8K, (photorealistic: 1.4), middreams, t-shirt, ———————————————————————————————————————— Recommended reverse prompts: losses, bad anatomy, bad hands, text, error, missing fingers, extra digit, lower digits, collapsed, best quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blur, perhaps Anatomy, bad hands, text, error, missing fingers, extra digits, feed digits, crawled, best quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blur, extra fingers, bad hands, extra hands, extra fingers, extra fingers, (extra digits and hands and fingers and legs and arms: 1.4), (deformed fingers: 1.2), (long fingers: 1.2), (ba fingers: 1.2) d-artist anime, extra legs, losses, bad anatomy, bad hands, text, Error, missing fingers, extra digits, feeder digits, crawled, best quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, long arms, ———————————————————————————————————————— This model currently has shortcomings, with few overfitting in the dataset, and it is not recommended to use full body and hand models. The evolution is lacking and will be optimized in the official version, but they are all beautiful models..... Currently, there is not enough support for nfsw, but it is not XX.... The model is still being improved, but after discussing these few points, I will put them out for use as soon as they are visible. I will gradually optimize them... We will strengthen lighting, photography, multi angle, and XXcos categories in the future. Due to the incomplete development of SD2.1 derivatives, the comment section will also be updated to include necessary derivative adjustment tools such as Lora.... Thank you all for your support 提示词相关性(CFGScale):2~5:前四张图片对应CFG;2,3,4,5。 此版本为SD-2.1-768底模 此本吧模型不再对SD1.5提供支持 平行光写实 正向提示词建议面部详细一点,不支持1girl直出,类似于sdxl更好。但尽量是词语或者短句 。对于不同网站的线上作图似乎对cfg的引导性有差距,这一点可以自行尝试确认,通常来来说1~7,只是风格展现形势不同。——————————————————————————————————————————————————————— 示例正向提示词:realistic,nsfw:2,detailed face,1girl,solo,long hair,Jewelry necklace,earrings,jewelry,complexdetails,8K,(photorealistic:1.4),midbreasts,t-shirt, ——————————————————————————————————————————————————————— 推荐反向提示词:lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts,signature, watermark,username,blurry, 或者 anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts,signature, watermark, username, blurry,extra finger,bad hand,extra hands,extra fingers,(extra digit and hands and fingers and legs and arms:1.4),(deformed fingers:1.2),(long fingers:1.2),(bad-artist-anime),extra legs,lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username,longarms, ——————————————————————————————————————————————————————— 此模型目前缺陷,数据集少有点过拟合,不建议出全身和手,演化性有所欠缺,待正式版优化,但都是美女模子。。。。。目前对nfsw支持但不够XX。。。。模型还在完善中只是这几论下来,画的能看就放出来先用着,等我慢慢优化。。。后续会加强光影,摄影和多角度,以及XXcos类。由于SD2.1衍生品不够完善,在后面也会更新评论区有需要的lora等衍生调节工具。。。。 在此感谢大家对我的支持

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated images

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.