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.
This model is for Animals / Creatures and Furries but can do way more :
Because it's an Flux Kontext model its main use
is image to image keep that in mind.
This model can do:
Photorealistic
Digital Art
Anime
Comic
Vector Graphics
Line art
Stickers
can write short text
furry
etc
This is the Flux Kontext variant of Ratatoskr Flux
The use case is for example for editing any picture made with the ratatoskr model series you can find in my profile but its working with any given pictures too.
Changelog:
V1: First Release Version
this is a block merged model made with the Original Kontext Model, and Parts of Ratatoskr Flux and Sleipnir Flux
Note: this is "Just" V1 and not directly trained on the Ratatoskr Dataset yet but i will use this block merge for the starting point for an actual finetune (V2) so there will for sure some Updates in the future.
V2:
This is the first trained Version that is using like i mentioned the V1 Block merged version
Its trained now at 175 paired images i created on the Ratatoskr Database. Because of the difference of captaining of kontext to my standard model database i did write all the caption by hand that alone took over 9 hours the training time itself did took some days...
the training helped a lot to "repair the damage" of the block merge with the standard flux kontext model
way more consistent
better in sfw and nsfw
the model is compatible also with my furry enhancer to some point tested with 0.7 strength
Made by Freek22
Please check out my other models too and give like to support my work ;-)
Description
V1 First model Release
FAQ
Comments (11)
I must be missing something.
Trying to use this model as Kontext model, but for me it works rather like basic flux. It tends to change image drastically, even when prompted heavily to retain composition.
Was hoping to get less censored Kontext, but it seems just got uncensored flux.
Also noticed it allows generate images with raster layer still active (in Invoke), which normally can't be done with Kontext model, only with base flux or sdxl model.
its because its a block merged model but i did start actual training already... like i did mentioned in the description.
freek22 Ah, cool. My bad for not readying it properly then. Waiting for real Kontext then!
Redwyrm released today the first trained version i also included the used workflow in the pictures
freek22 Awesome, thx!
Hm, still struggling to make it work as Kontext.
Here is quick examples.
Original image generated simply in flux. Woman on the beach, nothing special.
Image posted by Redwyrm
Then i tried modify it with base Kontext model, asking retain composition, but putting same woman in business attire
Image posted by Redwyrm
(ignore low quality, i did it with minimal amount of steps)
And finally i asked the same but with your checkpoint
Image posted by Redwyrm
It did something entirely different.
And finally, when i using your checkpoint, then loading reference image, it doesn't allow me to use Kontext model to process reference image
https://i.vgy.me/v7TWl8.png
Redwyrm well you can see i made all gallery images with my kontext model did worked fine for me (comfy workflow in all images)
Redwyrm i am using the official kontext workflow for comfy
freek22 Well, maybe it's somehow just incompatible with Invoke...
Redwyrm possible not tested with invoke at all
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



















