Instructions to use JoyFusionAI/Anima-2.9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use JoyFusionAI/Anima-2.9B with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Cosmos
How to use JoyFusionAI/Anima-2.9B with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Mirror Anima-2.9B preview-v1 from Gazingstars123/Anima-2.9B
Browse files
README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: circlestone-labs-non-commercial-license
|
| 4 |
+
license_link: https://huggingface.co/circlestone-labs/Anima/blob/main/LICENSE.md
|
| 5 |
+
base_model: Gazingstars123/Anima-2.9B
|
| 6 |
+
pipeline_tag: text-to-image
|
| 7 |
+
library_name: diffusion-single-file
|
| 8 |
+
tags:
|
| 9 |
+
- anima
|
| 10 |
+
- cosmos
|
| 11 |
+
- comfyui
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Anima-2.9B
|
| 15 |
+
|
| 16 |
+
Unmodified mirror of [Gazingstars123/Anima-2.9B](https://huggingface.co/Gazingstars123/Anima-2.9B) (preview-v1) for
|
| 17 |
+
JoyFusion's model downloads. Every file here is byte-identical to the upstream repository.
|
| 18 |
+
|
| 19 |
+
Anima-2.9B is a community fine-tune and layer expansion of [circlestone-labs/Anima](https://huggingface.co/circlestone-labs/Anima):
|
| 20 |
+
the transformer was expanded from 28 to 40 blocks (about 2.9B parameters) and trained on additional anime and
|
| 21 |
+
illustration data. It uses the same Qwen3-0.6B text encoder and Qwen-Image VAE as Anima 2B.
|
| 22 |
+
|
| 23 |
+
| File | Variant | Size | SHA-256 |
|
| 24 |
+
|---|---|---|---|
|
| 25 |
+
| `Anima-2.9B-preview-v1.safetensors` | BF16 | 5,843,204,206 | `0b3020d1b906155f7eb30667622723e87160632c8c7a5f1c93bdce685f2a346d` |
|
| 26 |
+
| `Anima-2.9B-preview-v1_int8_convrot.safetensors` | INT8 (convrot) | 3,082,486,758 | `cfb6ee2dde085de2b1c52b3fbe098dbc8c9ebd24f290c59755ab2c5f9291d396` |
|
| 27 |
+
|
| 28 |
+
`config.json` and `expand_manifest.json` are copied from upstream and describe the layer expansion.
|
| 29 |
+
|
| 30 |
+
Upstream recommends 28–50 steps, CFG 3.5–5 and resolutions such as 832×1216 or 1152×1536. There is no distilled
|
| 31 |
+
(Turbo) variant yet.
|
| 32 |
+
|
| 33 |
+
## License
|
| 34 |
+
|
| 35 |
+
Anima is licensed by CircleStone Labs LLC under the CircleStone Labs Non-Commercial License (see `LICENSE.md`), and
|
| 36 |
+
Anima-2.9B falls under its derivative-model category. Use and distribution are permitted for non-commercial purposes
|
| 37 |
+
only. See `NOTICE` for the required attribution notice.
|