Unfortunately I had to upload the model again, losing all download progress and reviews due to problems with civitai.
Model created by combining different types of NSFW checkpoints.
If you enjoy my content, please consider supporting it ☕☕☕ . Thank you.
Instructions:
Instructions, recommended parameters:
Sampling steps: 25-30
Sampling method: Euler A
Upscaler: 4x- Anime Sharp
Noise: 2.5 / 4.0
CFG: 6,5 / 7
Description
FAQ
Comments (7)
Is this checkpoint the only one that would work with your embeddings?
No, my embeds should work with any checkpoint
Textual Inversion focuses tokens and weights them internally according to the trained data. They do not contain any inference data unlike LoRA or a whole external prediction network (like Hypernetworks) so it relies on the model knowledge you use it upon...
As a general rule
TI (Embedding) and Hypernetworks does not contain inference data => Model needs to have the knowledge
LoRA contains inference data => model does not need to have the knowledge but it should be compatible with the inference data
what is the difference between 1.3 and 1.2
what VAE would you suggest with this model. Looks good.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.