Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
GoodHands-beta2.safetensors
516 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<betterhands-b2>
About This Model
STABLE DIFFUSION 1.5 · LoRAs
Created by
_Envy_
on Civitai
__html__This model is a LoCon. You MUST install the Lycoris extension for it to load.I'm using Lora Block Weight. I believe you can also use Additional Networks and SD Webui Lycoris.UPDATE 4/27/2023: I've hit a training plateau so I'm in the process of adding a bunch more images to the dataset, including some more complicated stuff like intertwined fingers. I'm probably going to have to drop the learning rate some more, so things may be slower from here on. I'll keep everyone posted as things progress.UPDATE: Prompting advice for beta 2:This is a completely new train on top of vanilla Stable Diffusion 1.5. I did this based on the advice of a fellow enthusiast, and it's surprising how much more compatible it is with different model. It doesn't mess with the style of your model at all as far as I can tell, and it really only affects hands and occasionally arms, leaving everything else untouched.It seems to work best at a strength of 1, although turning up higher than that (1.5, 2, etc) can help it on some images at the cost of making it worse on others. No need to mess with your CFG scale, as it doesn't cause things to overcook at these levels.Freely mix it with other LoRAs.I've had best results putting "nice hands, perfect hands" in the positive prompt (increasing the weight makes things worse), and "(extra fingers, deformed hands, polydactyl:1.5)" in the negative prompt. This is on EnvyMix v1 (and probably RevAnimated), but YMMV for other models."Bad hands" negative embedding
Creator notes
This model is a LoCon. You MUST install the Lycoris extension for it to load. I'm using . I believe you can also use and . UPDATE 4/27/2023: I've hit a training plateau so I'm in the process of adding a bunch more images to the dataset, including some more complicated stuff like intertwined fingers. I'm probably going to have to drop the learning rate some more, so things may be slower from here on. I'll keep everyone posted as things progress. UPDATE: Prompting advice for beta 2: - This is a completely new train on top of vanilla Stable Diffusion 1.5. I did this based on the advice of a fellow enthusiast, and it's surprising how much more compatible it is with different model. It doesn't mess with the style of your model at all as far as I can tell, and it really only affects hands and occasionally arms, leaving everything else untouched. - It seems to work best at a strength of 1, although turning up higher than that (1.5, 2, etc) can help it on some images at the cost of making it worse on others. No need to mess with your CFG scale, as it doesn't cause things to overcook at these levels. - Freely mix it with other LoRAs. - I've had best results putting "nice hands, perfect hands" in the positive prompt (increasing the weight makes things worse), and "(extra fingers, deformed hands, polydactyl:1.5)" in the negative prompt. This is on EnvyMix v1 (and probably RevAnimated), but YMMV for other models. - "Bad hands" negative embeddings appear to make it worse, although I haven't tested this extensively. - As usual, this won't work miracles, but I do find that over a large number of images, it does make things generally better on average. Hopefully this will continue to improve with a few more nights of training. Prompting advice for alpha 3 and beta 1: - Note that this advice is for RevAnimated 1.2. YMMV with other models. - It overcooks things a bit, but you need the strength set to 1.0 for it to really work well. You can work around this by reducing the CFG value to 5 or 6 or so. I've had good luck with enabling the dynamic thresholding extension and setting it to mimic CFG 5, and then I can set my CFG value to 9 or 10 and things come out fine. - I tried using it with another LoRA and got some pretty strange results, so YMMV there as well. Right now I'm just trying to get it to work consistently in a simple use case. - Oddly, I think it's regressed a bit on hands in neutral positions, but it's noticeably better at more complicated interactions, such as holding objects (which is why I have so many pictures of blacksmiths and librarians in the example images). - Keep your prompts simple and it tends to do better. - With RevAnimated, I tend to get 1 or 2 usable images out of every 8, with a bunch of other ones that are pretty close and can probably be fixed with inpainting. Prompting advice for alpha 2: - It's getting stronger now, and it works best around strength 1. Setting it to 1.3 like the previous version will make things look bad. - My negative prompt is still "(extra fingers, deformed hands:1.15), (worst quality, low quality, poor quality, bad quality:1.35)" - I had good luck just putting "nice hands" in the main prompt. Prompting advice For alpha 1: - Your prompt should contain these words: "beautiful hands, perfect hands, fingernails". I've had the best luck with them towards the middle, and at no emphasis. - The alpha1 LoCon seems to work best at a strength of around 1.3 (on RevAnimated 1.1, where I'm testing it right now -- YMMV for other models) - Don't use negative embeddings for improving hands. When I removed badhandv4 from my negative prompt, things improved noticeably. You may want to try without any negative embeddings at all. I haven't used them for a while now. - My negative prompt is: "(extra fingers, deformed hands:1.15), (worst quality, low quality, poor quality, bad quality:1.35)", which I arrived at through a lot of experimentation adjusting strengths and terms one at a time. It should work decently well. - This all gives me hope that there's a real shot at solving hands on SD 1.5. Even with good prompting, I'm generally not getting perfect results, but things are close. I'll consider this done when it creates well-formed hands without having to add anything to the positive or negative prompt. Now back to your regularly scheduled readme... I'm testing the theory that maybe the reason MidJourney's hands are so much better now is that they just took the time to specifically train a network on a high quality set of pictures of hands, and literally nobody else has actually tried. This LoRA definitely isn't at MidJourney levels yet, but I've been training it over night for several nights now and adding to the dataset where it appears deficient, and quality seems to be steadily improving. As such, I'm going to post this now so people can start using it. Consider this an early alpha -- I'll only stop updating once it stops getting better. Example images are cherry-picked. Please don't expect this model to make all of your hand generations better. It may even make some of them worse, so you should evaluate its usefulness on a large number of images and not just one. If it works for you like it does for me, the a lot of your results should be the same or better quality (some will just be bad in different ways).
119,378 downloads · 10,728 likes on Civitai
SHA256
BA43B0EFEE61ACE63EAA443AEDC11432423A8398A9EEC11E5CA33B9CEC9A21D8
ModelTrends.ai Model ID
#2299
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
DPM++ 3M SDE Exponential
Steps
27
Guidance
4.5
Seed
672529995
Size
576x816
Prompt
a castle sitting on the mountain surrounding by the trees, foggy, dark night, moon and clear sky, (masterpiece),((ultra-detailed)), (highly detailed CG illustration),(expressionless), (best quality:1.2), High quality texture, intricate details, detailed texture, High quality shadow, <lora:add_detail:0.5>, <lora:GoodHands-vanilla:1>, <lora:detailed_notrigger:0.7>, <lora:picxer_real:0.7>
Negative prompt
(((hat, glove, collar, nail polish, choker))), EasyNegative,paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot,extra fingers,fewer fingers, (bad-hands-5:1.4), (badPromptVersion2_v10:0.8), (badv5:0.6), ng_deepnegative_v1_75t, BadDream,OverallDetail,
Settings
Sampler
DPM++ 3M SDE Exponential
Steps
27
Guidance
4.5
Seed
1743938333
Size
1728x2496
Clip skip
2
Prompt
troodon, opening mouth, sharp teeth, running in forest, (masterpiece),((ultra-detailed)), (highly detailed CG illustration),(expressionless), (best quality:1.2), High quality texture, intricate details, detailed texture, High quality shadow, <lora:add_detail:0.5>, <lora:GoodHands-vanilla:1>, <lora:detailed_notrigger:0.7>, <lora:picxer_real:0.7>
Negative prompt
EasyNegative,paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)),(badPromptVersion2_v10:0.8), (badv5:0.6), ng_deepnegative_v1_75t, BadDream,OverallDetail,
Settings
Sampler
DPM++ 2M Karras
Steps
25
Guidance
20
Seed
1869144976
Size
512x768
Clip skip
2
Prompt
realistic shadows, depth of field, bokeh, <lora:add_detail_realistic:1>, 1 girl, adult (elven:0.7) woman, amber eyes, dark brown wedge cut hair, <lora:GoodHands-beta2:0.8>, solo, from front, front view, (full body:0.6), (closed eyes:1.1), detailed background, detailed face, (<lora:kVoidEnergy-000001:0.5>, V0id3nergy, void theme:1.1) glowing magical third eye on forehead, eye tattoo, illusionist, psychic powers, awareness, mind control, hypnosis, enchantment, psychomancy, clairvoyance, mesmerizing, aura, mind portal, mind energy, magical blue psychic energy emanating, updraft, magic in background, ethereal atmosphere,
Negative prompt
cartoon, painting, illustration, (worst quality, low quality, normal quality:2), watermark, logo,(male, man, boy, masculine:1.2), (open eyes, eyes open, wink:1.2),
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
7
Seed
2617259163
Size
520x464
Clip skip
2
Prompt
HDR,UHD,8K,best quality,masterpiece,<lora:GoodHands-beta2:1>,white background,1girl,1boy,(((,<lora:HeartHandsFailure:0.8>,,IncrsHHFail,heart hands duo))),(sad:1.5),<lora:CHAR-Stark:0.8>,StarkFrieren,red jacket,black shirt,white sash,black pants,bandages,gloves,red eyes BREAK <lora:CHAR-Fern:0.8>,FernFrieren,very long hair,purple eyes,(purple pupils),white dress,black robe BREAK <lora:CHAR-Frieren:0.8>, Frieren,twintails,earrings,FrierenBase,twintails,earrings,white capelet,striped shirt,white skirt,long sleeves,belt,black pantyhose,BREAK <lora:himmel_sousou_no_frieren:0.7>,himmel_sousou_no_frieren,blue hair,blue eyes,
Negative prompt
logo,text,badhandv4,EasyNegative,ng_deepnegative_v1_75t,rev2-badprompt,verybadimagenegative_v1.3,negative_hand-neg,mutated hands and fingers,poorly drawn face,extra limb,missing limb,disconnected limbs,malformed hands,ugly,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,NegfeetV2,
Settings
Sampler
DPM++ SDE Karras
Steps
35
Guidance
7
Seed
3794752853
Size
2816x4224
Clip skip
2
Prompt
<lora:add_detail:0.4> <lora:GoodHands-beta2:1> <lora:GoldenTech-20:0.7> (masterpiece, best quality, realistic, detailed, crisp:1.2), intricate details, goldentech, (low angle, picture), (shrex), <lora:ShrekDoguVersion2:1> (goldsuit, yellow necktie, sunglasses, hands on chest), <lora:attire_goldensuit:0.5> gleam, shine, backlighting,
Negative prompt
(low quality, worst quality:1.4), easynegative, BadDream, UnrealisticDream, text, watermark, signature, ugly, disfigured, deformed, low quality, blurry, deformed, lowres, ugly, username, artist name, watermark, trademark, out of frame
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
7
Seed
281575278
Size
1024x1024
Clip skip
2
Prompt
HDR,UHD,8K,best quality,masterpiece,1girl,mature female,large breasts,model,slender,tall,<lora:GoodHands-beta2:1>,<lora:404:1>,Incrs404,english text,<lora:gijinkaseries_civitai-18:0.8>,civitai-chan,braided bangs,labcoat,shirt,shirt tucked in,necklace,(((<lora:VergilStatusMeme:1>,VergilStatusMeme))),1boy,vergil,<lora:(character)vergil:0.7>,Sheath the katana,<lora:ChihiroUnsheathingAKatanaMeme:0.8>,IncrsUnsheathingAKatanaMeme,sheath,holding sheath,
Negative prompt
logo,text,badhandv4,EasyNegative,ng_deepnegative_v1_75t,rev2-badprompt,verybadimagenegative_v1.3,negative_hand-neg,mutated hands and fingers,poorly drawn face,extra limb,missing limb,disconnected limbs,malformed hands,ugly,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,NegfeetV2,
Settings
Sampler
DPM++ 2M Karras
Steps
32
Guidance
9.5
Seed
107
Size
512x768
Prompt
(masterpiece, best quality:1.3), 1girl, Icelander blacksmith, nice hands, in a smithy, auburn hair<lora:GoodHands-beta2:1>
Negative prompt
(extra fingers, deformed hands, polydactyl:1.3), (worst quality, low quality, poor quality, bad quality:1.35)
Settings
Sampler
DPM++ 2M
Steps
20
Guidance
7
Seed
1735555088
Size
512x768
Clip skip
2
Weight used
1
Prompt
witch
Negative prompt
twins, blond girl, hurt, girlish,blurry face, younger, cute, scared, beard, 2girl,fat, big head, animal ear, text, 1980style, fur, eastern, china, japan, agly, cute, bad face bad anatomic, realistic,
AI Models for Image, Video & Text Generation
betterhands b2 is a LoRA for the Stable Diffusion 1.5 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion 1.5 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models