Project All In One (AIO)
Please Red Description
Questions/Feedback/Updates
Visit my thread on the Unstable Diffusion Discord
Buy me a coffee ❤
https://ko-fi.com/ndimensional
All donations will be used to fund the creation of new Stable Diffusion fine-tunes and open-source AI tools.
This model is a merge between all of my previously released models and, some unreleased models.
Going forward, all future models and updates to existing models will also be added/updated on this model.
ChangeLog :
12/1/23 V9
Rebuilt from the ground up (as usual).
Included updated models for:
Unreleased version of SciStyle
Added 4 upcoming fine-tunes
7/31/23 V6
Rebuilt from the ground up.
Added models : Cine Diffusion, Electric Eden, Based Model, Another Damn Art Model (ADAM), Lomostyle, Doomer Boomer, and an unreleased Anime fine-tune
Recommended Settings
Clipskip: 1
ENSD: 31337
Sampler:
DPM++ SDE Karras, 30 - 40 steps
DPM++ 2M Karras, 30 - 60 steps
Heun, 20 steps, Sigma Churn = 1
Euler, 20 - 70 steps, Sigma Churn = 1
These parameters are not strictly required, experiment around with other samplers and parameter values. You might find something that works better for you.
Check out my other models (also the models used in the merge)
SDXL
Boomer Art Model - https://civarchive.com/models/163139/boomer-art-model-bam
SD1.5
Doomer Boomer - https://civarchive.com/models/118247?modelVersionId=128239
Lomostyle - https://civarchive.com/models/109923/lomostyle
Another Damn Art Model (ADAM) - https://civarchive.com/models/104898?modelVersionId=112493
Based Model - https://civarchive.com/models/83991?modelVersionId=89262
Electric Eden - https://civarchive.com/models/64355/electric-eden
Cine Diffusion - https://civarchive.com/models/50000/cine-diffusion
WonderMix - https://civarchive.com/models/15666/wondermix
Experience - https://civarchive.com/models/5952/experience
Elegance - https://civarchive.com/models/5564/elegance
VisionGen - Realism Reborn -https://civarchive.com/models/4834/visiongen-realism
LoRA
Pant Pull Down - https://civarchive.com/models/11126/pant-pull-down-lora
Special thanks to rocp for the witch and French maid prompt used in the sample pictures, @nutrition for copious research/testing of various sampling methods/parameters, and to everyone in the Unstable Diffusion Discord community that make doing this a more fun and enjoyable experience.
Description
Project All In One (AIO) v4.5
Now Includes:
Updates from Experience and Clarity
Two new unreleased models
Added Eris to the merge
Note: Civitai renames files after download, removing the decimal. Your downloaded files may appear as AIO_45.safetensors after downloading.
FAQ
Comments (8)
Great model !
If possible can you also add, for the v4.5, the smaller 2gb pruned-fp16 version ?
Yes, civitai is still quite bugged for model updates atm. I had to use a workaround to get the model uploaded. Once a proper fix is implemented I'll get the fp16 and .ckpt version uploaded.
@ndimensional Thank you ! Can you signal the event in this comment thread, so that I'll be notified by the platform ?
I'll have to try the new version, looks way better. I'm thinking of merging this with Deliberate for a custom merge, what do think a good ratio percentage is?
I honestly haven't used deliberate much, but from what I've seen, maybe an add difference merge at 25%. With AIO being model A, Deliberate B, AIO C. If you get memory errors - use the model converter extension to prune AIO to -emaonly and convert it's precision to FP16. Use the full FP32 in your A slot and the pruned-emaonly version in C.
Usually 20-25% is all you need for the merged model to have a noticeable effect. If you want more of deliberate, then I'd suggest an add difference merge at ~65%.
Good luck!
@ndimensional thanks, 25% is exactly what I was considering too.
4.5 working good so far, what's the difference of PF16 and ckpt ver?
FP32 is 32bit, FP16 is 16bit. Three are subtle differences for training but for all intents and purposes - FP16 is a smaller file size. .ckpt is in Pickle tensor format (how tensors are stored). This is really only useful for those who use software that doesn't support .safetensors format.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.