ANIMAGINE XL 2.0
Download the model here, CivitAI hash checker is bad.
Huggingface link: https://huggingface.co/Linaqruf/animagine-xl-2.0
Gradio Demo : https://huggingface.co/spaces/Linaqruf/Animagine-XL
Training model is very expensive, please consider to support us at : https://ko-fi.com/linaqruf
Overview
Animagine XL 2.0 is an advanced latent text-to-image diffusion model designed to create high-resolution, detailed anime images. It's fine-tuned from Stable Diffusion XL 1.0 using a high-quality anime-style image dataset. This model, an upgrade from Animagine XL 1.0, excels in capturing the diverse and distinct styles of anime art, offering improved image quality and aesthetics.
Model Details
Developed by: Linaqruf
Model type: Diffusion-based text-to-image generative model
Model Description: This is a model that excels in creating detailed and high-quality anime images from text descriptions. It's fine-tuned to understand and interpret a wide range of descriptive prompts, turning them into stunning visual art.
License: CreativeML Open RAIL++-M License
Finetuned from model: Stable Diffusion XL 1.0
Gradio & Colab Integration
Animagine XL is accessible via Gradio Web UI and Google Colab, offering user-friendly interfaces for image generation:
Gradio Web UI:
Google Colab:
Further information please visit Official Repository at Huggingface
Description
Initial commit
FAQ
Comments (10)
looks amazing :DD Does the training dataset have male characters too ?
How many images was this trained on?
ComfyUI does not seem to allow using 915 as a width. Will 912 work roughly the same, or should I be worried about loss of quality?
It says
TypeError: expected Tensor as element 0 in argument 0, but got DictWithShape
Time taken: 0.2 sec.
when i tried to generate an image.
how to solve?
Which VAE is this? It doesn't seem to be one of the usual suspects.
Congratulations!
I downloaded it and It Failed to Load the Checkpoint. Any Advices?
I like the model. However, allegedly there is a bug in the way you packaged it, according to
https://github.com/Stability-AI/StableSwarmUI/issues/150#issuecomment-1794245317
It seems that LoRa didn't work with this model
I cant't use it with controlNet.
It says:
RuntimeError: mat1 and mat2 shapes cannot be multiplied (77x2048 and 768x320)
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.