Instructions to use Bedovyy/Anima-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Bedovyy/Anima-FP8 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
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,11 @@ base_model_relation: quantized
|
|
| 9 |
|
| 10 |
# FP8 Quantized model of ANIMA
|
| 11 |
|
|
|
|
|
|
|
| 12 |
## Quantized layers
|
|
|
|
|
|
|
| 13 |
```json
|
| 14 |
{
|
| 15 |
"format": "comfy_quant",
|
|
@@ -22,9 +26,40 @@ base_model_relation: quantized
|
|
| 22 |
}
|
| 23 |
```
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
## Sample
|
| 26 |
|
| 27 |
-
| bf16 | fp8 |
|
| 28 |
-
|-----|------|
|
| 29 |
-
||
|
|
|
|
|
|
|
| 30 |
|
|
|
|
| 9 |
|
| 10 |
# FP8 Quantized model of ANIMA
|
| 11 |
|
| 12 |
+
There's two model. FP8 and FP8Mixed. FP8Mixed quantized smaller layer, so expect better quality.
|
| 13 |
+
|
| 14 |
## Quantized layers
|
| 15 |
+
|
| 16 |
+
### fp8
|
| 17 |
```json
|
| 18 |
{
|
| 19 |
"format": "comfy_quant",
|
|
|
|
| 26 |
}
|
| 27 |
```
|
| 28 |
|
| 29 |
+
### fp8mixed
|
| 30 |
+
```json
|
| 31 |
+
{
|
| 32 |
+
"format": "comfy_quant",
|
| 33 |
+
"block_names": ["net.blocks."],
|
| 34 |
+
"rules": [
|
| 35 |
+
{ "policy": "keep", "match": ["blocks.0.", "blocks.1.", "blocks.27.", "adaln_modulation", "v_proj"] },
|
| 36 |
+
{ "policy": "float8_e4m3fn", "match": ["q_proj", "k_proj", "output_proj", "mlp"] },
|
| 37 |
+
{ "policy": "nvfp4", "match": [] }
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
## Generation speed
|
| 43 |
+
|
| 44 |
+
Tested on
|
| 45 |
+
- RTX5090 (400W), ComfyUI with torch2.10.0+cu130
|
| 46 |
+
- Generates 832x1216, 30steps, cfg 4.0, er sed, simple
|
| 47 |
+
|
| 48 |
+
| Dtype (Quant) | Sage Attn | it/s | Time (s) | Relative Speedup (%) |
|
| 49 |
+
| ------------- | --------- | ---- | -------- | -------------------- |
|
| 50 |
+
| bf16 | X | 4.33 | 7.07 | 0% |
|
| 51 |
+
| bf16 | O | 4.66 | 6.59 | +7.6% |
|
| 52 |
+
| fp8mixed | X | 4.79 | 6.42 | +10.6% |
|
| 53 |
+
| fp8mixed | O | 5.25 | 5.87 | +21.3% |
|
| 54 |
+
| fp8 | X | 4.94 | 6.23 | +14.1% |
|
| 55 |
+
| fp8 | O | 5.40 | 5.72 | +24.7% |
|
| 56 |
+
|
| 57 |
+
|
| 58 |
## Sample
|
| 59 |
|
| 60 |
+
| bf16 | fp8mixed | fp8 |
|
| 61 |
+
|-----|------|------|
|
| 62 |
+
||||
|
| 63 |
+
||||
|
| 64 |
+
|
| 65 |
|