docs: readme
Browse files
README.md
CHANGED
|
@@ -20,6 +20,15 @@ tags:
|
|
| 20 |
**Original model**: [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev)<br/>
|
| 21 |
**GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
---
|
| 24 |
|
| 25 |
![FLUX.1 [dev] Grid](./dev_grid.jpg)
|
|
|
|
| 20 |
**Original model**: [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev)<br/>
|
| 21 |
**GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.
|
| 22 |
|
| 23 |
+
| Quantization | OpenAI CLIP ViT-L/14 Quantization | Google T5-xxl Quantization | VAE Quantization |
|
| 24 |
+
| --- | --- | --- | --- |
|
| 25 |
+
| FP16 | FP16 | FP16 | FP16 |
|
| 26 |
+
| Q8_0 | FP16 | Q8_0 | FP16 |
|
| 27 |
+
| (pure) Q8_0 | Q8_0 | Q8_0 | FP16 |
|
| 28 |
+
| Q4_1 | FP16 | Q8_0 | FP16 |
|
| 29 |
+
| Q4_0 | FP16 | Q8_0 | FP16 |
|
| 30 |
+
| (pure) Q4_0 | Q4_0 | Q4_0 | FP16 |
|
| 31 |
+
|
| 32 |
---
|
| 33 |
|
| 34 |
![FLUX.1 [dev] Grid](./dev_grid.jpg)
|