File size: 2,703 Bytes
cf50d12 7da4374 fd3a586 d29eeb0 fd3a586 d29eeb0 fd3a586 d29eeb0 fd3a586 d29eeb0 fd3a586 d29eeb0 fd3a586 d29eeb0 fd3a586 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 | ---
license: other
license_name: circlestone-labs-non-commercial-license
license_link: https://huggingface.co/circlestone-labs/Anima/blob/main/LICENSE.md
language:
- en
pipeline_tag: text-to-image
base_model:
- circlestone-labs/Anima-Base-v1.0-Diffusers
base_model_relation: quantized
library_name: diffusers
---
For more information (including how to compress models yourself), check out https://huggingface.co/DFloat11 and https://github.com/LeanModels/DFloat11
Feel free to request for other models for compression as well (for either the `diffusers` library, ComfyUI, or any other model), although models that use architectures which are unfamiliar to me might be more difficult.
### How to Use
#### `diffusers`
```python
import torch
from diffusers import ModularPipeline, CosmosTransformer3DModel
from dfloat11 import DFloat11Model
from transformers.initialization import no_init_weights
with no_init_weights():
transformer = CosmosTransformer3DModel.from_config(
CosmosTransformer3DModel.load_config(
"circlestone-labs/Anima-Base-v1.0-Diffusers",
subfolder="transformer"
),
torch_dtype=torch.bfloat16
).to(torch.bfloat16)
DFloat11Model.from_pretrained("mingyi456/Anima-Base-v1.0-DF11-Diffusers", device="cpu", bfloat16_model=transformer)
text_encoder = DFloat11Model.from_pretrained("mingyi456/Qwen3-0.6B-Base-DF11", device = "cpu")
pipe = ModularPipeline.from_pretrained("circlestone-labs/Anima-Base-v1.0-Diffusers")
pipe.update_components(text_encoder=text_encoder.model)
pipe.update_components(transformer=transformer)
pipe.load_components(dtype=torch.bfloat16)
DFloat11Model.from_pretrained(
"mingyi456/Anima-Base-v1.0-text_conditioner-DF11-Diffusers",
device = "cpu",
bfloat16_model=pipe.text_conditioner
)
pipe.to("cuda")
image = pipe(
prompt="masterpiece, best quality, 1girl, solo, city lights",
generator=torch.Generator("cpu").manual_seed(114514),
).images[0]
image.save("image anima")
```
#### ComfyUI
Refer to this [model](https://huggingface.co/mingyi456/Anima-DF11-ComfyUI) instead.
### Compression details
This is the `pattern_dict` for compression:
```python
pattern_dict = {
r"transformer_blocks\.\d+": (
"norm1.linear_1",
"norm1.linear_2",
"attn1.to_q",
"attn1.to_k",
"attn1.to_v",
"attn1.to_out.0",
"norm2.linear_1",
"norm2.linear_2",
"attn2.to_q",
"attn2.to_k",
"attn2.to_v",
"attn2.to_out.0",
"norm3.linear_1",
"norm3.linear_2",
"ff.net.0.proj",
"ff.net.2"
),
r"time_embed\.t_embedder": (
"linear_1",
"linear_2",
)
}
``` |