Badhandv4

Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.

PirateDiffusion Telegram

Pro studio (SpyGlass) Web

Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.

Best for power users. Full control over models, settings and workflows in a browser studio.

Discord bot (Vector)

Best for communities. Add it to your own server and run any workflow from a channel.

Unified Editor Web

One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.

Civitai Web

Pay per use

Generate on Civitai's own site; every image is paid for with Buzz credits.

Local apps

Requires setup

Set up local programs if your computer has capable hardware.

ModelDuel Web

Pay per use

Generate the same prompt on up to 50 checkpoint/base models at a time.

Rent a GPU on the cloud

Graydient Cloud GPU

331,574 downloads · 18,007 likes on Civitai

Flat fee, unlimited use. This model installs with one click.

RunPod Cloud GPU

Charged by the minute

Rent a GPU by the minute and set the model up yourself.

Created by

Euge_

on Civitai

Creator notes

介绍（Chinese Version）简介此文本嵌入（text embedding）为负面文本嵌入。它能够在对画风影响较小的前提下改善AI生成图片的手部细节。如果它让你的模型表现得比以前更糟，请勿使用它。您可与其他负面文本嵌入一同使用。虽然它是为 AnimeIllustDiffusion 模型设计的，但您也可以在其他模型上使用。它似乎在较高的 CFG Scale 下（>=11）表现得更好。如何使用对于 AUTOMATIC1111 WebUI 用户 - 下载模型文件； - 将模型文件放置于您 Stable Diffusion WebUI 目录下的 "embeddings" 文件夹内； - 打开 WebUI，在负面提示词框内填入 “badhandv4” 以触发效果。对于 ComfuUI 用户 - 下载模型文件； - 将模型文件放置于您 ComfyUI 目录下的 "models/embeddings" 文件夹内； - 打开 ComfyUI，在负面提示词框内填入 “embedding:badhandv4” 以触发效果。 SDXL 版本我将 badhandv4 移植到了 SDXL 格式的 embedding 上。下载地址参见： Introduction (英文版本) Introduction This text embedding is a negative text embedding. It can improve the hand details of AI-generated images with less impact on the style of painting. If it makes your model behave worse than before, please do not use it. You can use it with other negative text embeddings. Although it was designed for AnimeIllustDiffusion model, you can use it on other models as well. It performs better with higher CFG scale (>=11). Quick Start For AUTOMATIC1111 WebUI User - Download model file ; - Move the model file to the "embeddings" folder in your Stable Diffusion WebUI directory; - Lanuch WebUI. Enter "badhandv4" into the negative prompt box to trigger its effect. For ComfyUI User - Download model file ; - Move the model file to the "models/embeddings" folder in your ComfyUI directory; - Lanuch ComfyUI. Enter "embedding:badhandv4" into the negative prompt box to trigger its effect. SDXL version I converted badhandv4 to SDXL format embedding. For downloading, see:

Trigger words

badhandv4

SHA256

5E40D722FC3D0C2DECB62DEBFAF8058DB30CCDAE9AB00FF64B183907B435708E

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Also ranked: #112 Hottest AI model · #18 Hottest Stable Diffusion 1.5 model

Not this creator?

Get your own badge

badhandv4 Popularity Trend

Heat score, last 12 months

Heat score

8,685°

This week

▼

0.1%

8,687° then, 8,685° now

This month

▼

0.3%

8,693° then, 8,685° now

Past year

▼

3.6%

8,773° then, 8,685° now

7,000°

Floor

The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.

+1,656°

Civitai downloads

331,574 downloads of this exact version on Civitai. Downloads are the heaviest ingredient and are counted on a log scale: ten times the downloads adds the same 300°, so a model with a million downloads is not a thousand times hotter than one with a thousand. The six download sources share that one term, split between them in proportion to their counts.

+638°

Likes

18,007 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.

−609°

Age

−609° because the SD15 weights came out in 2022. Every model inherits the age of the weights it is built on: 150° a year, up to 750°, and it keeps growing until then. Without it the top of the list would be 2022 and 2023 checkpoints on the strength of downloads that had years to pile up.

Show detailed breakdown

Every number on this site can be checked. This model's heat score is 8,685°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.

1
Start at the floor.
Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
7,000°
running total
2
Add the downloads.
331,574 download-equivalents in all, from Civitai downloads. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+1,656°
8,656°
running total
3
Add the likes.
18,007 likes and thumbs up, at half the weight of a download.
+638°
9,294°
running total
4
Take off the age.
The SD15 weights came out in 2022: 150° a year, up to 750°, growing until then.
−609°
8,685°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,685°

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.

Example renders

Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.

Get this prompt

Render by Enraken on Civitai

Settings

Sampler

Euler a Karras

Steps

Guidance

Seed

997428451160355

Size

896x1152

Clip skip

Weight used

Prompt

realistic, vibrant, detailed. a cinematic photograph classily depicts a prestigious beautiful woman dressed in an all white dress. The woman has no face. Her head is a sphere, a colorful gradient foreign planet, and not a human head. Her outfit is adorned by luxurious gold trim and other attire. Her skin is tan with smooth rough textures. She has a very detailed planetary sphere for her head that emits natural weather phenomenon and neon ethereal ozonous layers, swirls, and hues. The image is sharp and professional with studio quality. The contrast and style is very sharp, but liquid and vivid. Gorgeous background and details with subtle hints of illumination. glass, ether, spirit, breath, light, energy. Particles, high density quality, vibrant colors and hues. The overall style of the image is highly stylish, dynamic and free-flowing elegance., modest, sfwlazypos

Negative prompt

watermark, (pupilless eyes:1.2) smudgy, (bad quality:1.15), (worst quality:1.3), censored, (jpeg artifacts), (patreon username, patreon logo:1.1), (bad hands:1.1), ugly, (extra fingers:1.2), (extra toes:1.2), ng_deepnegative_v1_75t, easynegative, badhandv4,

Render by Nourdal on

Settings

Sampler

UniPC

Steps

Guidance

Seed

994

Size

512x512

Clip skip

Prompt

RAW photo, 8k uhd, Analog style, (Masterpiece, Best Quality, Highres:1.3), dramatic, cinematic, BREAK, (Isometric perspective:1.4) (Pixar style:1.2) (3D model render:1.3) of little (intricate:1.2) (ancient elven beach ruins:1.3), (deck chair, stairs, (palms:1.2), cars, rocks, sand castle:1.1), (overgrown desert, sand, well, shovel:1.05), ((white background:1.1), solid background, global illumination, raytracing, modeling, HDR, octane render, unreal render, miniature:1.2), (hyperdetailed, absurdres:1.1), BREAK, <lora:more_details:1.0>

Negative prompt

easynegative, badhandv4, bad-hands-5, BREAK, (Low Quality, Worst Quality, Lowres:1.3), (RAW photo, Analog style, photorealistic, landscape:1.3), semi-realistic, cartoon, anime, blurry, blurred,

Render by Zovya on

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

8.5

Seed

735323561

Size

512x768

Clip skip

Prompt

((best quality)), ((masterpiece)), (detailed), alluring succubus, ethereal beauty, perched on a cloud, (fantasy illustration:1.3), enchanting gaze, captivating pose, delicate wings, otherworldly charm, mystical sky, (Luis Royo:1.2), (Yoshitaka Amano:1.1), moonlit night, soft colors, (detailed cloudscape:1.3), (high-resolution:1.2)

Negative prompt

3d, cartoon, anime, sketches, (worst quality, bad quality, child, cropped:1.4) ((monochrome)), ((grayscale)), (bad-hands-5:1.0), (badhandv4:1.0), (easynegative:0.8), (bad-artist-anime:0.8), (bad-artist:0.8), (bad_prompt:0.8), (bad-picture-chill-75v:0.8), (bad_prompt_version2:0.8), (bad_quality:0.8)

Render by 7915 on

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

Seed

2215488272

Size

512x768

Clip skip

Prompt

[(white background:1.5)::5] hexagon,(detailed face:1.2),smile,chinese style,immortal demeanor, long-haired man, peaks, deep ravines, stars, turbulent winds, soaring dragons, cross-shaped sword, purple clouds, giant birds, portal, smoke, flames, mystical runes, ancient robe, red petals, halo,lightning,thunder,<lora:lightAndShadow_v10:0.3>, <lora:lightlineArtLora_v10:0.3> ,<lora:yoneyamaMaiStyleLora_yoneyamaMaiV2:0.5>, <lora:gachaSplashLORA_gachaSplash31:0.4>

Negative prompt

EasyNegative,worst quality, low quality, badhandv4

Render by rodrigolourenco234 on

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

Seed

2759166727

Size

768x1152

Clip skip

Prompt

(masterpiece, max quality, absurdres:1.4), colorful, perfect picture, wallpaper, full body shot of one man casting (blue lightning bolt spell:1.5), wizard, long white hair, brown eyes, long white beard, white flowing wizard robes, mountain with castle background, night sky with dark clouds, detailed, intricate, detailed background, colorful, realistic background, realistic sky, good pose, dynamic pose, (cinematic, cinematic camera angle, perfect lighting, perfect shading), volumetric lighting, subsurface scattering <lora:add_detail:.5> <lora:muscle_slider_v1:-1> <lora:weight_slider_v2:-.5> <lora:fantasyV1.1:.25>

Negative prompt

badhandv4, bad-hands-5, badquality-neg, EasyNegativeV2, bad-artist, Asian-Less-Neg, ng_deepnegative_v1_75t, (deformed hands, extra fingers, missing fingers, inverted hands, broken hands, broken fingers, missing hands, 6 fingers, 4 fingers, deformed fingers, interlaced hands:1.7), (staff, wand, scepter, dagger, cane, spear, lance, weapon, mace, weapons, shield, stick, walking stick:1.2), (low quality, worst quality, bad quality:1.4)

Render by rodrigolourenco234 on

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

Seed

2265146695

Size

768x1024

Prompt

full body low view shot of (one) brittish old man, wizard, (casting blue lightning magic:1.3), (night), wizard (robes), long white beard, long white hair, grasslands, castles, dark clouds, night sky, detailed, intricate, (detailed fantasy background), ((fantasy art style)), (oil painting style:1.4), (photorealistic:1.5), (best quality, hi-res, masterpiece:1.4), good anatomy, good composition, good proportions, good design, good pose, dynamic pose, realistic background, realistic sky, cinematic, cinematic camera angle, dark fantasy illustration, detailed, intricate, (perfect lighting, perfect shading), dreamlike diffuse ethereal lighting, subsurface scattering, photorealistic, solo, (mature adult:1.5) <lora:add_detail:0.15> <lora:fantasyV1.1:0.25> <lora:muscle_slider_v1:-1.5> <lora:epi_noiseoffset2:.3>

Negative prompt

bad-artist, badhandv4, bad-hands-5, badquality-neg, EasyNegativeV2, (Asian-Less-Neg,:1.2), (deformed hands, extra fingers, missing fingers, inverted hands, broken hands, broken fingers, missing hands, 6 fingers, 4 fingers, deformed fingers, interlaced hands, duplicated hands:1.9), (words, text, logo, brand, font, signature:1.5), bad proportions, bad anatomy, tail, devil, (staff, scepter, spear, lance, javelin, mace, weapon, weapons, shield, wand, cane, baton, stick:1.7), (elf ears, pointy ears)

Render by rodrigolourenco234 on

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

Seed

430506039

Size

768x1024

Prompt

full body of (one) brittish old man, a wizard casting a (blue lightning bolt spell) from his hands, from the top of a mountain, (at night), wearing white wizard (robes), long white beard, long white hair, dramatic pose, detailed, intricate, (detailed fantasy background), dim lighting, volumetric lighting, fantasy art style, best quality, hi-res, masterpiece, good anatomy, good composition, good proportions, good design, good pose, realistic background, realistic sky, cinematic, cinematic camera angle, dark fantasy illustration, detailed, intricate, (perfect lighting, perfect shading), subsurface scattering, photorealistic, solo, oil painting style, (mature adult:1.5), <lora:add_detail:0.15> <lora:fantasyV1.1:0.25> <lora:muscle_slider_v1:-1.5>

Negative prompt

bad-artist, badhandv4, bad-hands-5, badquality-neg, EasyNegativeV2, (deformed hands, extra fingers, missing fingers, inverted hands, broken hands, broken fingers, missing hands, 6 fingers, 4 fingers, deformed fingers, interlaced hands, duplicated hands:1.8), (words, text, logo, brand, font, signature:1.5), bad proportions, bad anatomy, tail, devil, (staff, sword, weapon, scepter, lance, spear:1.5)

Render by rodrigolourenco234 on

What is ComfyUI? A beginner's guide to nodes, workflows and the first graph

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

Seed

260508006

Size

512x683

Prompt

full body of (one) brittish old man, a wizard casting a (lightning bolt spell), from the top of a mountain, (at night), wearing white wizard (robes), long white beard, long white hair, detailed, intricate, (detailed fantasy background), dim lighting, volumetric lighting, fantasy art style, best quality, hi-res, masterpiece, good anatomy, good composition, good proportions, good design, dynamic pose, good pose, realistic background, realistic sky, cinematic, cinematic camera angle, dark fantasy illustration, detailed, intricate, (perfect lighting, perfect shading), subsurface scattering, photorealistic, solo, oil painting style, (mature adult:1.5), <lora:add_detail:0.15> <lora:fantasyV1.1:0.25> <lora:muscle_slider_v1:-1.5>

Negative prompt

Run Locally

How to install

Dec 17, 2025

Open Civitai Download

badhandv4.pt

PickleTensor · fp16 · full

Downloads are served by Civitai. Some creators ask for a Civitai login first.

More by this creator

ArtiWaifu Diffusion

STABLE DIFFUSION XL 1.0

Useful Quality Embeddings deformityv6

BASE

Useful Quality Embeddings aid291

EMBEDDING

Useful Quality Embeddings badv5

EMBEDDING

Similar Models

【Concept】Dogeza 概念土下座

No.407 超写实手办 Super realistic figure style

LORA