Instructions to use Ava2000/Mossacannibalis_Anima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Ava2000/Mossacannibalis_Anima with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("oron1208/OOO_Anima", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Ava2000/Mossacannibalis_Anima") prompt = "masterpiece, best quality, traditional media, " image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Upload The style of Mossacannibalis.
Browse files
The style of Mossacannibalis.
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
The style of Mossacannibalis.
|
| 2 |
+
|
| 3 |
+
I made this lora to try and reproduce the style of Mossacannibalis. I used mostly their 40k artwork in this LoRa, but without the keywords (I forgot).
|
| 4 |
+
|
| 5 |
+
Prompting Anima
|
| 6 |
+
|
| 7 |
+
Might be the last upload, because my Mangamaster showcase image got flagged and after that the whole model was unpublished (just a bit of fuming here).
|
| 8 |
+
|
| 9 |
+
My recommendations: For the quality tags I use masterpiece, best quality, traditional media, and I use the following for my negatives: worst quality, low quality, score_1, score_2, score_3, bad hands, mutated hands, extra fingers, missing fingers, extra digits, fewer digits, fused fingers, deformed hands, poorly drawn hands, bad anatomy, deformed fingers, hands with too many fingers, signature,
|
| 10 |
+
|
| 11 |
+
You can use the artist tag @mossacannibalis but I haven't noticed a big change from it. But might help in different checkpoints.
|
| 12 |
+
|
| 13 |
+
Trigger: mossacannibalis,
|
| 14 |
+
|
| 15 |
+
Strength: 0.6 - 1.0
|