Diffus
Commencer
modèles/Fast Negative Embedding (+ FastNegativeV2) - v1.0 Normal [preferred for styles]

Fast Negative Embedding (+ FastNegativeV2) - v1.0 Normal [preferred for styles]

Lykon
|
12/5/2025
|
1:14:39 AM
| Discussion|
0
Dark blue-skinned woman named Ranni wearing a large pointed wizard hat with intricate details, multiple arms folded and hands together, with glowing blue eyes under a starry night sky.
Split screen close-up portrait of two male cyborgs, Raiden with silver hair and Jetstream Sam with dark hair and beard, showcasing detailed mechanical elements.
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 red house situated on a rocky island surrounded by calm water reflecting the house and nearby trees under a grey sky with the moon visible, in a soft minimalistic digital painting style.
Detailed portrait of a woman with black hair wearing high-tech night vision goggles emitting a green glow and a black mask, set against a dark background.
Anime-style girl with long black hair, tattoos, wearing a black dress, and making a peace sign. AI generated image using Stable Diffusion.
A smiling female police officer in a blue uniform, standing against a warm sunset backdrop. This is an AI-generated image using Stable Diffusion.
AI generated image of an anime girl with blonde hair, wearing a dark outfit and sitting in an abandoned building with a melancholic expression.
AI-generated image of a blonde woman in a white dress with a playing card created using Stable Diffusion
Stylish portrait of a red-haired woman using stable diffusion AI.
AI generated image using stable diffusion of a Western girl with a cowboy hat, wearing tight blue jeans and a white top, posing against a wooden background.

Paramètres recommandés

samplers

DPM++ SDE Karras, DPM++ 2S a Karras

steps

20 - 50

cfg

7 - 9

resolution

512x768, 512x704, 512x640

other models

DreamShaper_6_BakedVae (b76cc78ad9), AnyLoRA_bakedVae_fp16_NOTpruned (b775b13509), AnimePastelDream_Soft_bakedVae (ff5cb8e794), DreamShaper_5_beta2_BakedVae (6d492d946c), anything-v4.5-pruned (e4b17ce185)

Paramètres haute résolution recommandés

upscaler

8x_NMKD-Superscale_150000_G, Latent (bicubic antialiased), R-ESRGAN AnimeVideo, None, R-ESRGAN General 4xV3

upscale

1.4 - 1.8

steps

10 - 25

denoising strength

0.37 - 0.6

Conseils

Use Fast Negative Embedding in the negative prompt only, not in positive prompts.

If the embedding is too overpowering, apply it with weight, e.g., (FastNegativeEmbedding:0.9).

FastNegativeV2 version added which should not require lowering the weight.

Report in comments if styles are not maintained when using style loras.

Points forts de la version

This mostly relies on the base model and loras and tries to keep the style unchanged, while making the picture look good.

Sponsors du créateur

Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕

Fast Negative Embedding

Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕

Token mix of my usual negative embedding. This way it's faster to use and easier to reproduce.

I'm also working on a much stronger one that doesn't preserve styles but it's good on base models without style loras applied. I plan to upload it during the next week, so be sure to leave a ❤️ to be notified of future updates.

This is very much a work in progress, but since I'm already using it in examples, I thought I should upload it.

It should keep styles on all my style loras. If not please tell me in the comments.
Additionally, if you find this too overpowering, use it with weight, like (FastNegativeEmbedding:0.9).

Update: added FastNegativeV2. It shouldn't be necessary to lower the weight.

Of course, don't use this in the positive prompt.
This includes Nerf's Negative Hand embedding.

Contributeur

Lykon avatar

Lykon

Précédent
JDM Legends - Mazda RX-7
Suivant
DCT(Dream Come True) SDXL and SD1.5 - Dream Come True XL v2.0
Utiliser ce modèle

Détails du modèle

Type de modèle

TextualInversion

Modèle de base

SD 1.5

Version du modèle

v1.0 Normal [preferred for styles]

Hash du modèle

687b669d82

Mots entraînés

FastNegativeEmbedding

Créateur

Lykon's avatar
Lykon

Discussion

Veuillez vous log in pour laisser un commentaire.

Images par Fast Negative Embedding (+ FastNegativeV2) - v1.0 Normal [preferred for styles]

Dark blue-skinned woman named Ranni wearing a large pointed wizard hat with intricate details, multiple arms folded and hands together, with glowing blue eyes under a starry night sky.
Split screen close-up portrait of two male cyborgs, Raiden with silver hair and Jetstream Sam with dark hair and beard, showcasing detailed mechanical elements.
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 red house situated on a rocky island surrounded by calm water reflecting the house and nearby trees under a grey sky with the moon visible, in a soft minimalistic digital painting style.
Detailed portrait of a woman with black hair wearing high-tech night vision goggles emitting a green glow and a black mask, set against a dark background.
Anime-style girl with long black hair, tattoos, wearing a black dress, and making a peace sign. AI generated image using Stable Diffusion.
A smiling female police officer in a blue uniform, standing against a warm sunset backdrop. This is an AI-generated image using Stable Diffusion.
AI generated image of an anime girl with blonde hair, wearing a dark outfit and sitting in an abandoned building with a melancholic expression.
AI-generated image of a blonde woman in a white dress with a playing card created using Stable Diffusion
Stylish portrait of a red-haired woman using stable diffusion AI.
AI generated image using stable diffusion of a Western girl with a cowboy hat, wearing tight blue jeans and a white top, posing against a wooden background.

Images avec embedding

Vampiric enchantress with glowing red eyes, clad in black armor and velvet gown, holding a large red glowing sword inside a gothic ruined castle with moonlight and fog.
A vampiric enchantress with glowing purple eyes and pale skin in a dramatic macro close-up, wearing a dark, intricately detailed gown with red jewels, set against a moonlit ruined gothic castle surrounded by mist.

Images avec negative

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

Images avec outil

A furry humanoid character with a backpack and axe walking through a post-apocalyptic landscape. This is an AI generated image using Stable Diffusion.