Diffus
Inizia
modelli/Deep Negative V1x - V1 75T

Deep Negative V1x - V1 75T

Kate Thompson
|
7/1/2024
|
5:47:19 PM
| Discussion|
0
A highly detailed digital artwork of an ornate woman adorned with golden jewelry, surrounded by colorful feathers and vibrant red flowers set against an abstract, fractal-inspired background.
Young woman dressed in a cowgirl outfit with a brown hat and red scarf riding a dark brown horse outdoors near wooden structures under a clear sky.
Girl in a white cat costume with a red bow, cat ears, fluffy tail, posing dynamically with glowing Halloween pumpkin in background
Two women dressed in elegant hanfu with hair styled in buns, sitting face-to-face, holding a glowing white lotus flower with closed eyes.
A tall slender woman with piercing blue eyes, wearing a detailed black leather jacket over a black lacy bra, ripped blue jeans, and layered chain necklaces, standing against a neutral textured wall.
A captivating concubine with a sensual grace stands illuminated by warm lantern light in a Persian harem, adorned in silk garments and golden jewelry.
A woman with wet hair and wearing a see-through wet dress walks on a rainy street at night under a dark blue theme with reflections on the wet road.
Side profile of a woman with a forlorn expression, dressed in an ornate outfit with leaf patterns, set against a warm fractal art backdrop with deep shadows.
A long path stretches through a dystopian town devastated by an atomic explosion, with engulfing flames and a massive mushroom cloud of smoke and fire looming overhead.
Close-up portrait of a devilish young woman with curly red hair, black horns, red lipstick, and a playful black dress against a fiery red smoky background.
A melancholic female figure resembling Atlas in a classical John William Waterhouse style, with dark drapery, gold accents, and a somber, bleak background.
Two young female characters with long purple and white hair wearing baseball uniforms, pitching on a baseball field at sunset with a stadium background.

Prompt Consigliati

masterpiece,PureErosFace_V1,best quality,[highly detailed face:0.1],1girl,a full body portrait of a 21 years old beautiful gorgeous cute busty Korean kpop girl,pink eyes,(jieunc_kor:0.8),long hair,slender body,black hair,detailed face,(grapefruit),perfect anatomy,(temple in background),contrapposto,sitting,Cannon EOS 5D MARK III,kimono,50mm Sigma f/1.4 ZEISS lens,medium breasts,F1.4,light smile,1/800s,arms behind back,ISO 100,photorealistic,trending on instagram

Prompt Negativi Consigliati

disgusting,worst quality,low quality,logo,text,watermark,username

NG_DeepNegative_V1_75T,(worst quality,worst quality,low quality:1.4),low quality,logo,text,monochrome,nipples,nude

Parametri Consigliati

samplers

Euler a

steps

20 - 40

cfg

11

resolution

512x768

Suggerimenti

Use embedding with negative prompts like (worst quality, low quality, logo, text, watermark, username).

For models trained with more than 75 tokens, consider using smaller token versions to avoid errors.

Punti Salienti della Versione

put it in negative prompts

Sponsor del Creatore

If you use SDXL, recommended this 👉 DeepNegative for SDXL version

This embedding will tell you what is REALLY DISGUSTING🤢🤮

So please put it in negative prompt😜

⚠This model is not trained for SDXL and may bring undesired results when used in SDXL.

If you use SDXL, recommended this 👇

another deep-negative:

TOP Q&A

  • how to use TI model?

https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion

  • what is negative prompt?

https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Negative-prompt

[Special Reminder] If your webui reports the following errors:

- CUDA: CUDA error: device-side assert triggered

- Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed

- XXX object has no attribute 'text_cond'

Please try using a model version other than 75T.

> The reason is that many scripts do not handle overly long negative prompt words (greater than 75 tokens) properly, so choosing a smaller token version can improve this situation.

[Update:230120] What does it do?

These embedding learn what disgusting compositions and color patterns are, including faulty human anatomy, offensive color schemes, upside-down spatial structures, and more. Placing it in the negative can go a long way to avoiding these things.

-

What is 2T 4T 16T 32T?

Number of vectors per token

[Update:230120] What is 64T 75T？

64T: Train over 30,000 steps on mixed datasets.

75T: embedding limit maximum size, training 10,000 steps on a special dataset (generated by many different sd models and special reverse processing)

Which one should choose?

  • 75T: The most ”easy to use“ embedding, which is trained from its accurate dataset created in a special way with almost no side effects. And it contains enough information to cover various usage scenarios. But for some "good-trained-model" may hard to effect

    and, change about may be subtle and not drastic enough.

  • 64T: It works for all models, but has side effect. so, some tuning is required to find the best weight. recommend: [( NG_DeepNegative_V1_64T :0.9) :0.1]

  • 32T: Useful, but too more

  • 16T: Reduces the chance of drawing bad anatomy, but may draw ugly faces. Suitable for raising architecture level.

  • 4T: Reduces the chance of drawing bad anatomy, but has a little effect on light and shadow

  • 2T: ”easy to use“ like T75, but just a little effect

Suggestion

Because this embedding is learning how to create disgusting concepts, it cannot improve the picture quality accurately, so it is best used with (worst quality, low quality, logo, text, watermark, username) these negative prompts.

Of course, it is completely fine to use with other similar negative embeddings.

More examples and tests

How is it work?

I tried to make SD learn what is really disgusting with deepdream algorithm, the dataset is imagenet-mini (1000 images chosen randomly from the dataset again)

deepdream is REALLLLLLLLLLLLLLLLLLLLLY disgusting 🤮 and process of training this model really made me experience physical discomfort 😂

Backup

https://huggingface.co/lenML/DeepNegative/tree/main

Precedente
EasyNegative - EasyNegative_pt
Successivo
BadDream UnrealisticDream Negative Embeddings - BadDream v10
Usa questo modello

Dettagli del Modello

Tipo di modello

TextualInversion

Modello base

SD 1.5

Versione del modello

V1 75T

Hash del modello

54e7e4826d

Parole addestrate

ng_deepnegative_v1_75t

Creatore

lenML's avatar
lenML

Discussione

Per favore log in per lasciare un commento.

Immagini di Deep Negative V1x - V1 75T

A highly detailed digital artwork of an ornate woman adorned with golden jewelry, surrounded by colorful feathers and vibrant red flowers set against an abstract, fractal-inspired background.
Young woman dressed in a cowgirl outfit with a brown hat and red scarf riding a dark brown horse outdoors near wooden structures under a clear sky.
Girl in a white cat costume with a red bow, cat ears, fluffy tail, posing dynamically with glowing Halloween pumpkin in background
Two women dressed in elegant hanfu with hair styled in buns, sitting face-to-face, holding a glowing white lotus flower with closed eyes.
A tall slender woman with piercing blue eyes, wearing a detailed black leather jacket over a black lacy bra, ripped blue jeans, and layered chain necklaces, standing against a neutral textured wall.
A captivating concubine with a sensual grace stands illuminated by warm lantern light in a Persian harem, adorned in silk garments and golden jewelry.
A woman with wet hair and wearing a see-through wet dress walks on a rainy street at night under a dark blue theme with reflections on the wet road.
Side profile of a woman with a forlorn expression, dressed in an ornate outfit with leaf patterns, set against a warm fractal art backdrop with deep shadows.
A long path stretches through a dystopian town devastated by an atomic explosion, with engulfing flames and a massive mushroom cloud of smoke and fire looming overhead.
Close-up portrait of a devilish young woman with curly red hair, black horns, red lipstick, and a playful black dress against a fiery red smoky background.
A melancholic female figure resembling Atlas in a classical John William Waterhouse style, with dark drapery, gold accents, and a somber, bleak background.
Two young female characters with long purple and white hair wearing baseball uniforms, pitching on a baseball field at sunset with a stadium background.

Immagini con concept

Side profile of a girl with a hair bun wearing a transparent glass helmet against an orange background with delicate Japanese text above.
Portrait of a pink-skinned cyborg girl with yellow eyes and black sclera, featuring steampunk elements, mechanical limbs, an antique clock background, and a mechanical heart.
Ethereal woman with long flowing hair in a dark lace dress standing amid glowing fireflies at sunset above clouds with a glowing orb and streak of blue light in the background.

Immagini con negative

Black and white zombie illustration with dark background and expressive pose.