AlbedoBase XL Pre
The refiner is unnecessary, and VAE is included.
Please preview the next version of the AlbedoBase XL model and provide your feedback here. Once i gather and incorporate all the feedback, i will release the official version to the AlbedoBase XL side.
v2.1pre-beta
I revised the merging process and incorporated four checkpoints, originally designed for enhancement, throughout the system.
v2.1pre-alpha
I revised the merging process and incorporated four checkpoints, originally designed for enhancement, throughout the system.
The spec grid(424.4 MB): download
v2.0pre-alpha
The algorithm has been changed, and the DPO has been excluded. This is a test 2.0 version.
v2.0pre-DPO
- The Merge formula has been updated.
- The DPO model has been added.
- Full utilization of negative prompts is now available.
- Support for Clip Skip 2 has been introduced.
- Enhanced detail clarity for all samplers is achieved as the step count increases.
The spec grid(424.3 MB): download
v1.6pre
I've changed the algorithm of the Merge itself.
v1.5pre
I have written a custom script to converge the existing AlbedoBase XL models into one. Intricately aligning the row and column weights of all U-NET and CLIP blocks according to a unique equation, may produce a merging effect different from previous methods. It is still experimental, and I am so serious that I am immersed in the challenge of writing a paper independently (though I do not have a master's or doctorate in the field).
The spec grid(399.2 MB): download
I enjoy this work, and my curiosity and passion will not cease even if a better model comes out and AGI is developed.
Description
The algorithm has been changed, and the DPO has been excluded. This is a test 2.0 version.
FAQ
Comments (5)
Why you upload all 2 days a "NEW" model ???
its non sense !!!
you say "give me feedback"
and how many pics 10 ?
and the discussion here 7 ???
Im mean what are you doing ???
And you don't say anything about what might be better?
or what the strengths or weaknesses of the model are ?!?!
nobody is forcing you to download or test these pre-releases.
you can just wait for the official release of a new version here (currently 1.3) https://civitai.com/models/140737/albedobase-xl
I had hoped to update the official version by Christmas, but that didn't pan out. Now, I'm racing to get the official version updated by January 1st. You have no idea how much testing I'm doing all day long, how desperately I cling to people's feedback. And for the DPO version, I've already received ample feedback and have incorporated it. It's far from nonsense. Just look at the reviews, photos, and discussions from others. The shortcomings of the previous model have already been identified.
@albedobond amazing work one of the best models ty
i see ...
where you get that feedback ?
and i dont say the model is bad ;)
but ok in 2 years we have 100 good models, nobody knows which one is it good for ...
in LLM (large language models) it give some ranking (human, facts, coding, chat and so on) maybe we need such stuff for txt2img models ?
maybe one hint, the models with turbo or LCM i get an error in kohya for lora training ... so its fast but at the moment you cant use it for training
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.