exosilica
This model is based on the beautiful HYC. Trigger word is hoacb. Work with all styles that I've tried so far. Always use vae-ft-mse-840000-ema-pruned. You can do eye experiments for changing her eye colors, eg: Deep Blue Eyes, Hazel Green Eyes. Play around with her hair as well, she works on Blonde, Black, Redhead and naturally is a Brunette.
For best results use Heun for sampling at 20-35 (so far tested).
CFG scale so far 9 (I use as default) have been working best.
What is hoacb?
hoacb is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user exosilica. Derived from the powerful Stable Diffusion (SD 1.5) model, hoacb 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 hoacb is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as photorealistic, babes, asian.
With a rating of 0 and over 0 ratings, hoacb is a popular choice among users for generating high-quality images from text prompts.
Can I download hoacb?
Yes! You can download the latest version of hoacb from here.
How to use hoacb?
To use hoacb, 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 hoacb, check out our crash course in AI image generation.
Popularity
Info
Latest version (hoacbLORAv2.safetensors): 1 File
About this version: hoacbLORAv2.safetensors
These are LORA extract of the original hoacb.ckpt, which is a smaller alternative to the original checkpoint model. The results obtained from this LORA extract may not be as strong as the original checkpoint model, but it can be useful for those who need to save space on their hard drive.
There are two LORA models available: the hoachlora.safetensors created from 128 DIM and the hoacbLORAv2.safetensors created at 8 DIM. Both of these models provide some resemblance to the original checkpoint, but they do not look exactly like the original checkpoint. These models are still a work in progress.
For the best results, it is recommended to use both of these LORA models at once, running CFG at 3-4 and the Sampler to DPM++ SDE Karras. This combination tends to provide a close resemblance to the original HOACB checkpoint. Although it may not be an exact match, this combination of LORA models still generate beautiful results and should be seen as an ongoing experiment.
