StablyDiffused's GobGirlz Mix
v2
stablydiffused
I first saw GobGirlz and was really excited for what it could do. After using it for a while it just consistently fell short of expectations to me. No offense to the model creator, it's still an excellent model, I just felt like it needed a little cleaning up. Well, I think I've done that. MajorX came to the rescue with his 2d POV model. It merged with GobGirlz excellently with some fantastic results and really made things pop quite a bit.
After that though I still felt like there was just a little something missing. I toyed around with quite a few combinations and landed on using Elldreth's Vivid (v1) Mix and it was also excellent. Note, you can't go overboard with Elldreth's Vivid otherwise it messes up all the features that MajorX 2d POV adds in there (the sex parts...). The result is something quite awesome that does GobGirlz in a spectacularly NSFW fashion (not that it wasn't NSFW already) and supports all the trigger words from both GobGirlz and MajorX 2d POV.
This does require the Anything v3 VAE (Attached for convenience). And because it includes Elldreth's Vivid, which in turn includes Dreamlike, there is a license on this, which is linked at the bottom of the description. Also, seeing as it includes MajorX POV and Elldreth's Vivid, it's capable of more than just goblin girls. It can do other things pretty well too.
NOTE: All prompts in the example images are using InvokeAI Syntax NOT Automatic1111 syntax. The main difference here is that 'term+' is equivalent to '(term)' ++ is equivalent to (()) and so on.
Also Also Note.... If you get a black image, that's a bug with the VAE, not with the model. Make sure you have the command argument --no-half-vae in your startup command line arguments to solve that issue.
Full Model Recipe:
Merge 1 = GobGirlz v1 (50%) + Major X's 2D POV Model v1.1 (50%)
Merge 2 = Merge 1 (75%) + Elldreth's Vivid Mix v1 (25%)
If you want to recreate something similar but without a license requirement, you could just recreate the Merge 1. this is still a fantastic merge at that point, it's just a little less, well... Vivid....
Models used in this merge:
https://civitai.com/models/3660/gobgirlz
https://civitai.com/models/3662/major-xs-2d-pov-model
https://civitai.com/models/2747/elldreths-vivid-mix
Dreamlike License:
https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0/blob/main/LICENSE.md
What is StablyDiffused's GobGirlz Mix?
StablyDiffused's GobGirlz Mix is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user stablydiffused. Derived from the powerful Stable Diffusion (SD 1.5) model, StablyDiffused's GobGirlz Mix has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that StablyDiffused's GobGirlz Mix is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, female, shortstack.
With a rating of 4.5 and over 2 ratings, StablyDiffused's GobGirlz Mix is a popular choice among users for generating high-quality images from text prompts.
Can I download StablyDiffused's GobGirlz Mix?
Yes! You can download the latest version of StablyDiffused's GobGirlz Mix from here.
How to use StablyDiffused's GobGirlz Mix?
To use StablyDiffused's GobGirlz Mix, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like StablyDiffused's GobGirlz Mix, check out our crash course in AI image generation.
Popularity
Info
Latest version (2): 3 Files
About this version: 2
Decided to test the same merge formula but substitute in Elldreth Imagination instead of Vivid and the results came out fantastic. The colors were more vibrant, textures were better (in most cases), and hands and eyes were a lot better (in some cases). I also tried the same formula with Vivider (Vivid 2.0) but don't recommend that. Vivider seems to completely kill gobgirlz for some reason and I can't get any goblins with that merge formula. But Imagination works wonders.
All images use the same prompts/seeds as v1 so you have them for direct comparison. Also as with V1 you want to use the Anything v3.0 VAE (attached for convenience) along with this model.
2 Versions
Go ahead and upload yours!
