This Lora was originally trained for SDXL, due to the improved performance of XL release in rendering very well nyloned feet, with different nylon clothes (pantyhose, stockings), and colors (black, tan, white). If you use SDXL please look at this Lora (RealNylonFeets for SDXL)
Due to many requests received, several training runs were performed to assess if an SD 1.5 Lora should be set with a good performance.
Taking into account that with SD 1.5 the AI feet rendering is still challenging, this Lora is at the moment my best result:
please read the instructions in the GENERATION FLOW paragraph to maximize results!
Triggering prompt keyword:
RealNylonFeetsLora weight:
A value of 0.6 to 0.9 is highly recommended. Higher values can trigger artifacts.
A base activation keyword for lora is:
<lora:RealNylonFeets:0.8>This Lora could be used both with realistic or manga checkpoints. Realistic Vision and Henmix_real were used to generate the demo gallery.
Sampling steps:
About 40-60 sampling steps.
Additional options
- The triggering keyword should be preceded by a color. Lora was trained with black, tan and white colors, but a good prompt should render also many other colors.
Black RealNylonFeets
Tan RealNylonFeets
White RealNylonFeets
- There are some different particulars than can be rendered, like painted toenails, that can be triggered by using the following tokens:
Painted toenails- Moreover is better to specify what kind of nylonwear is requested (Pantyhose, Stockings) adding a specific tokens:
pantyhose
stocking
For this purpose specific Loras for SD 1.5 can be added to the prompt, like:
GENERATION FLOW:
1) ControlNet is strongly recommended, during the first txt2img generation: canny or openpose approach is strongly recommended to avoid gross aberrations.
2) After a first round of txt2img, the best image should be refined using an img2img round, eventually adjusting the strength of some tokens.
3) Finally inpaint will be fundamental to refine feet details. If checkpoint include a specific inpaint model, its use is recommended.
A specific prompt is recommended for this step, focusing only on feet. For example:
<lora:RealNylonFeets:0.8> RAW Photo, black RealNylonFeets, RealNylonFeets painted toesIf toes part is affected by color aberration, in the negative prompt should be included the token:
reinforced toesThe details level of this Lora could drop in case of full body portraits (very little feet) or in case of many different Lora used together. Details can be rescued using inpaint algorithm only on feet, but in this case an upscale process is recommended if the original image is less than 1000 px.
Image dimensions
Better result are obtained with a base image of about 900 px dimension on the long image side with an image width/length ratio of 1.5. After the base generation upscaling is a good practice.
USE DEMO IMAGES PROMPTS AS REFERENCE
Final statements:
1. You are solely responsible for any creative work using this model.
2. You cannot use this model to intentionally produce or share illegal images or content.
3. Furthermore can't use this model for malicious, hurtful, defamatory, fraudulent or political purposes.
Description
FAQ
Comments (12)
does it work with footjobs?
it does, but probably a further inpaint step could be required.
@eternal_zero will give it a try thanks :D
When I try to use with with the Regional Prompter or Lora Mask extensions it keeps thinking this is an SDXL Lora and crashing.
it's the first time I noticed it. The Lora is trained on SD1.5 at all, but i will try with regional prompter too, to check it. is there any chance tha the problem could be related to Regional prompter?
@eternal_zero When I run it with with Lora Mask, it gives me this error: "assert cv_name is not None, f"conversion failed: {du_name}. the model may not be trained by sd-scripts."
AssertionError: conversion failed: lora_unet_input_blocks_4_1_proj_in. the model may not be trained by sd-scripts."
Latent Couple appears to have accepted it from the prompt. Haven't seen the output yet. Your other LORAs seem to work just fine.
@nylonticklegal386 Can you include a sample prompt... this sounds really strange to me.
@eternal_zero The prompt I'm trying right now:
```
AND (((tan ultra sheer RealPantyhose (((phpose))), nylon covered foot, dorisflexion, pantyhose, RealNylonFeets Reinforced Painted Toes, soles, foot tickling)))
<lora:RealNylonFeets:0.06>
0
AND
```
That's using Latent Couple Extension. When generating a preview, the rendering crashed and it spat this out: " RuntimeError: mat1 and mat2 shapes cannot be multiplied (308x768 and 2048x64)
@nylonticklegal386 To be really honest I have no idea about this problem. Other Loras I made are trained exactly in the same way, except for steps number and epochs. So same configuration, same number of samples, same dimension of images, everything the same. I'm very sorry, but I don't understand what's the reason of this bug. Only one last thing: except for regional prompter Lora is going well? All the other loras you used are going ok? Did you try to use a different extension similar to regional prompter? Thanks in advance for your report, and sorry for the lack of solutions...
@eternal_zero No worries, I just thought I'd bring it to your attention. I'll see if I can get it to work with Latent Couple.
Mystery solved - I also had the SDXL model downloaded and it was trying to activate that one instead of the SD1.5 model. Once I removed SDXL it works just fine.
@nylonticklegal386 thanks for the feedback!!!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.