HybridMix_Pony6_Port
Mod23_alt4_Intermediate1e
aaronchm
Pony ports of HybridMix_SDXL by merging in the CLIP text encoder of the EveryLoRA checkpoint by advokat. Will be doing further Pony merges going forward, which will be posted onto a new model page. This model page is for models ported from SDXL with some NSFW capability.
Edit - methodology used
(Added to description for more visibility since it was asked in a comment)
Simply merge the CLIP (text encoder) with the one from EveryLoRA, advokat hasn't released any details on how the CLIP for that model was created but it works well for the purpose of merging SDXL with Pony6 models. This is controlled by BASE (Supermerger) / CLIP (ComfyUI). UNET (image generation model) are the remaining layers (Supermerger) / MODEL (ComfyUI).
Both 1a and 1e are simply HybridMix_SDXL Mod7_050 UNET with different ratios for the CLIP. Merge ratio depends on what you want to achieve, higher Pony / lower SDXL ratio is more unstable but makes the model align much more to what would be expected of Pony models, whilst lower Pony / higher SDXL helps to retain the style of the model as with what I did in this merge.
However, UNET definitely requires more Pony to be merged in to get better results for NSFW, unless the SDXL checkpoint(s) being merged already has good NSFW knowledge, which mine do not.
What is HybridMix_Pony6_Port?
HybridMix_Pony6_Port is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user aaronchm. Derived from the powerful Stable Diffusion (Pony) model, HybridMix_Pony6_Port 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 HybridMix_Pony6_Port is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, base model, woman.
With a rating of 0 and over 0 ratings, HybridMix_Pony6_Port is a popular choice among users for generating high-quality images from text prompts.
Can I download HybridMix_Pony6_Port?
Yes! You can download the latest version of HybridMix_Pony6_Port from here.
How to use HybridMix_Pony6_Port?
To use HybridMix_Pony6_Port, 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 HybridMix_Pony6_Port, check out our crash course in AI image generation.
Popularity
Info
Version Mod23_alt4_Intermediate1e: 1 File
2 Versions
Go ahead and upload yours!
