In Norse mythology, Ratatoskr (Old Norse, generally considered to mean "drill-tooth" or "bore-tooth") is a squirrel who runs up and down the world tree Yggdrasil to carry messages between the eagle perched atop Yggdrasil and to the roots of the tree to Nidhogg.
WAN 2.1:
This WAN 2.1 Model is trained based on parts of the Ratatoskr Helheim / Flux Database
its made to animate Ratatoskr image outputs
so the model is better with animate , Animals , Anthro , Furry and Fantasy Creatures than the standard model.
the model can do SFW and NSFW
the model can handle different resolutions between 480p and 720p (even slightly above)
WAN V1.0:
I also recommend using any Ratatoskr based Pictures to generate Videos with it.
WAN 2.2 Hybrid V1.0:
This is an Hybrid model between parts a customized Wan 2.2 (WAN2.2-14B-Rapid-AllInOne T2V V1) and the V1 Version of Ratatoskr WAN 2.1
It's made with specific block merging and for now an wip model i will sure try also train in the future.
Like in the original WAN2.2-14B-Rapid-AllInOne Model the refiner is merged inside the model
so you can generate the image in with one ksampler but it needs 6 Steps instead of the 4 steps of the original Wan 2.2 Custom model and other Settings:
6 -10 Steps
Sampler Recommended: Uni PC BH2
Scheduler: Beta or sgm_uniform
cfg between 1 and 1.2 is tested
Overall this model is better with anthro and furry creatures than original also better in the nsfw area than standard WAN 2.2
Note: if you like T2V i made a Lora for that you can download and test it here: https://tensor.art/models/872785610920689931/Ratatoskr-WAN-Alpha-T2V-WIP-V0.4-WIP
There is also an Lora that i have build before i trained the model. i recommend to check it out.
the Model is trained at around 2700 pictures and 230 Videos.
if you wanna support my work please leave a like.
Description
This is the First Release Version
FAQ
Comments (11)
It would be cool if there was a text to video or FusionX version.
what i have is an T2V Lora https://tensor.art/models/872785610920689931/Ratatoskr-WAN-Alpha-T2V-WIP-V0.4-WIP
How effective is NSFW?
Posted some examples what is possible. But for more explicit NSFW I can recommend adding some Lora's even it may work without 😉👍 . In general it's better than the standard wan model but don't expect wonders
@freek22 Thank you. I was about to second this question. : 3
And thank you @2088996800908 for asking the question ^w^
@Pokefan That's great! Looking forward to it!
That's great! Looking forward to it
How do you train a full finetune? I don't know many tools that support it, in fact I haven't looked for many, but I would like to know if you could tell me what you used to train.
https://github.com/modelscope/DiffSynth-Studio/tree/main/examples/wanvideo/model_training/full rented some cloud computing h100 GPU. for the exact settings i had also technical help by them .... And this Fine-tune is a mix between Fine-tune and added Lora's I set on top.
@freek22 Thanks, the only way I knew existed was actually Diffsynth but I didn't get to test it, thanks.
@Alissonerdx no big deal to be honest without there help I was not able to do it even I have experience with sdxl and flux.