Download
1 variant available
License:
AnimaThe Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
Built on NVIDIA Cosmos
v2.0 reuses the same captioning and tags regime as v1.5 but with reduced data to 240k images due to constraints at 1280px but is multi res at 1024 and 1280px training somehow with more stable style across seeds and prompts, again all images have Natural Language captions, those Cross-Attention wasn't trained so https://github.com/An1X3R/Anima-Artist-Mixer will work as expected but at 1280px you hit a very big wall in speed and inference times, v2.0 preserves the ability to use latent styles without much dilution, model seems to like ModelSamplingFlux so samples were generated using it, mostly.
v1.5 a bit less stiff and less overwhelming style much less ai-generated style, all 400k images were trained with Natural Language and Tags on a rate of tags = 50%, nl = 10%, tags_nl = 20%, nl_tags = 20% so all images have Natural Language captions to preserve Anima's functionality on text and pure NL prompting, masterpiece/best quality are recommended still in pure NL.
Custom Mix of finetunes over Anima Preview 3 - Base, providing a familiar AI-generated Aesthetic into most seeds basically stabilizing to an extent the style variance over seeds, finetuned purely on 1024x1024 AR Buckets, the model aims to have its own default style without causing much dillution on latent characters or styles, issues from the base model have not been solved by this like multiple views being in negatives and it still happening on some wide shots, this model specifically trained some layers not all of them.
Usage Tips:
Positive Prompt:
masterpiece, best qualityNegative Prompt: blurry, jpeg artifacts,lowres, worst quality, low quality, bad hands, bad anatomy,signature, text, watermark, censor, bar censor, mosaic censorship, mosaic censor, patreon logo, patreon username, twitter username, twitter logo, chibi, blur, multiple views, sketch, monochrome or similars.
Technical Settings:
Sampler: Euler a, Euler, ER_SDE, SA Solver Pece
Steps: 20-28
Scheduler: Simple, Normal, Beta, Linear Quadratic
CFG Scale: 4.5-6.0
AuraFlowShift: 3.0 - 5.0
Resolution: 1024x1024 or any aspect ratio that falls within ~~1.048.576 pixels, 1280x1280 or any aspect ratio that falls within ~~1.638.400 pixels
If you want to support me, consider liking the model, and/or tipping buzz/donating to my Ko-fi, as this was finetuned on 8xL40s over 924K steps across all styles for version 2.0 at 1280px