Update README.md
Browse files
README.md
CHANGED
|
@@ -22,11 +22,16 @@ Normal K-quants are not working properly with SD3.5-Large models because around
|
|
| 22 |
- [sd3.5_large-q2_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-GGUF-mixed-sdcpp/blob/main/sd3.5_large-q2_k_4_0.gguf): Smallest quantization yet. Use this if you can't afford anything bigger
|
| 23 |
- [sd3.5_large-q3_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-GGUF-mixed-sdcpp/blob/main/sd3.5_large-q3_k_4_0.gguf)
|
| 24 |
- [sd3.5_large-q4_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-GGUF-mixed-sdcpp/blob/main/sd3.5_large-q4_k_4_0.gguf): Exacty same size as q4_0, but with slightly less degradation. Recommended
|
|
|
|
|
|
|
| 25 |
|
| 26 |
### Legacy types:
|
| 27 |
|
| 28 |
-
- [sd3.
|
| 29 |
-
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
## Outputs:
|
| 32 |
|
|
@@ -38,6 +43,9 @@ Sorted by model size (Note that q4_0 and q4_k_4_0 are the exact same size)
|
|
| 38 |
| q3_k_4_0 |  |  |  |
|
| 39 |
| q4_0 |  |  |  |
|
| 40 |
| q4_k_4_0 |  |  |  |
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
Generated with a modified version of sdcpp with [this PR](https://github.com/leejet/stable-diffusion.cpp/pull/397) applied to enable clip timestep embeddings support.
|
| 43 |
|
|
|
|
| 22 |
- [sd3.5_large-q2_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-GGUF-mixed-sdcpp/blob/main/sd3.5_large-q2_k_4_0.gguf): Smallest quantization yet. Use this if you can't afford anything bigger
|
| 23 |
- [sd3.5_large-q3_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-GGUF-mixed-sdcpp/blob/main/sd3.5_large-q3_k_4_0.gguf)
|
| 24 |
- [sd3.5_large-q4_k_4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-GGUF-mixed-sdcpp/blob/main/sd3.5_large-q4_k_4_0.gguf): Exacty same size as q4_0, but with slightly less degradation. Recommended
|
| 25 |
+
- [sd3.5_large_turbo-q4_k_4_1.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q4_k_4_1.gguf): Smaller than q4_1, and with comparable degradation. Recommended
|
| 26 |
+
- [sd3.5_large_turbo-q4_k_5_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/sd3.5_large_turbo-q4_k_5_0.gguf): Smaller than q5_0, and with comparable degradation. Very close to the original f16 already. Recommended
|
| 27 |
|
| 28 |
### Legacy types:
|
| 29 |
|
| 30 |
+
- [sd3.5_large_turbo-q4_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q4_0.gguf): Same size as q4_k_4_0, Not recommended (use q4_k_4_0 instead)
|
| 31 |
+
- [sd3.5_large_turbo-q4_1.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q4_1.gguf): Not recommended (q4_k_4_1 is better and smaller)
|
| 32 |
+
- [sd3.5_large_turbo-q5_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q5_0.gguf): Barely better and bigger than q4_k_5_0
|
| 33 |
+
- [sd3.5_large_turbo-q5_1.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q5_1.gguf): Better and bigger than q5_0
|
| 34 |
+
- [sd3.5_large_turbo-q8_0.gguf](https://huggingface.co/stduhpf/SD3.5-Large-Turbo-GGUF-mixed-sdcpp/blob/main/legacy/sd3.5_large_turbo-q8_0.gguf): Basically indistinguishable from the original f16, but much smaller. Recommended for best quality
|
| 35 |
|
| 36 |
## Outputs:
|
| 37 |
|
|
|
|
| 43 |
| q3_k_4_0 |  |  |  |
|
| 44 |
| q4_0 |  |  |  |
|
| 45 |
| q4_k_4_0 |  |  |  |
|
| 46 |
+
| q4_k_4_1 |  |  |  |
|
| 47 |
+
| q4_1 |  |  |  |
|
| 48 |
+
| q5_0 |  |  |  |
|
| 49 |
|
| 50 |
Generated with a modified version of sdcpp with [this PR](https://github.com/leejet/stable-diffusion.cpp/pull/397) applied to enable clip timestep embeddings support.
|
| 51 |
|