Text-to-Image
Diffusers
anima
lora
in-context
character-reference
ip-adapter-alternative
comfyui
anime
Instructions to use darask0/Anima-InContext-Character with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use darask0/Anima-InContext-Character with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("circlestone-labs/Anima", torch_dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("darask0/Anima-InContext-Character") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Add sample outputs (Yanineko, Nihon flag-girl)
Browse files
README.md
CHANGED
|
@@ -28,6 +28,16 @@ This is a LoRA + a small ComfyUI node pack. Unlike CLIP-embedding IP-Adapters, t
|
|
| 28 |
| Trained on | ~994k anime images / ~62k (reference≠target) character pairs |
|
| 29 |
| Use | attach 1–3 reference images → generate in any pose/scene |
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
---
|
| 32 |
|
| 33 |
## How it works
|
|
|
|
| 28 |
| Trained on | ~994k anime images / ~62k (reference≠target) character pairs |
|
| 29 |
| Use | attach 1–3 reference images → generate in any pose/scene |
|
| 30 |
|
| 31 |
+
## Samples
|
| 32 |
+
|
| 33 |
+
Original characters, unseen by the base model — generated from reference images alone.
|
| 34 |
+
|
| 35 |
+
| Yanineko (ヤニネコ) | Nihon / "Japan" flag-girl (国旗娘・日本) |
|
| 36 |
+
|:---:|:---:|
|
| 37 |
+
|  |  |
|
| 38 |
+
|
| 39 |
+
*Cat-eared original character with grey hair, tabby tail, casual outfit and yellow crocs (left); an original fox-shrine-maiden "flag-girl" personification of Japan in white-and-pink miko attire (right). Both reproduced in new renders from reference images.*
|
| 40 |
+
|
| 41 |
---
|
| 42 |
|
| 43 |
## How it works
|