morriszms commited on
Commit
6dd95a9
1 Parent(s): 39cc5b1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -12
README.md CHANGED
@@ -23,8 +23,16 @@ This repo contains GGUF format model files for [Gustavosta/MagicPrompt-Stable-Di
23
 
24
  The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
25
 
 
 
 
 
 
 
 
26
  ## Prompt template
27
 
 
28
  ```
29
 
30
  ```
@@ -33,18 +41,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
33
 
34
  | Filename | Quant type | File Size | Description |
35
  | -------- | ---------- | --------- | ----------- |
36
- | [MagicPrompt-Stable-Diffusion-Q2_K.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q2_K.gguf) | Q2_K | 0.076 GB | smallest, significant quality loss - not recommended for most purposes |
37
- | [MagicPrompt-Stable-Diffusion-Q3_K_S.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q3_K_S.gguf) | Q3_K_S | 0.084 GB | very small, high quality loss |
38
- | [MagicPrompt-Stable-Diffusion-Q3_K_M.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q3_K_M.gguf) | Q3_K_M | 0.091 GB | very small, high quality loss |
39
- | [MagicPrompt-Stable-Diffusion-Q3_K_L.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q3_K_L.gguf) | Q3_K_L | 0.095 GB | small, substantial quality loss |
40
- | [MagicPrompt-Stable-Diffusion-Q4_0.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q4_0.gguf) | Q4_0 | 0.099 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
41
- | [MagicPrompt-Stable-Diffusion-Q4_K_S.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q4_K_S.gguf) | Q4_K_S | 0.100 GB | small, greater quality loss |
42
- | [MagicPrompt-Stable-Diffusion-Q4_K_M.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q4_K_M.gguf) | Q4_K_M | 0.105 GB | medium, balanced quality - recommended |
43
- | [MagicPrompt-Stable-Diffusion-Q5_0.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q5_0.gguf) | Q5_0 | 0.114 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
44
- | [MagicPrompt-Stable-Diffusion-Q5_K_S.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q5_K_S.gguf) | Q5_K_S | 0.114 GB | large, low quality loss - recommended |
45
- | [MagicPrompt-Stable-Diffusion-Q5_K_M.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q5_K_M.gguf) | Q5_K_M | 0.118 GB | large, very low quality loss - recommended |
46
- | [MagicPrompt-Stable-Diffusion-Q6_K.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q6_K.gguf) | Q6_K | 0.129 GB | very large, extremely low quality loss |
47
- | [MagicPrompt-Stable-Diffusion-Q8_0.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/tree/main/MagicPrompt-Stable-Diffusion-Q8_0.gguf) | Q8_0 | 0.165 GB | very large, extremely low quality loss - not recommended |
48
 
49
 
50
  ## Downloading instruction
 
23
 
24
  The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
25
 
26
+
27
+ <div style="text-align: left; margin: 20px 0;">
28
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
29
+ Run them on the TensorBlock client using your local machine ↗
30
+ </a>
31
+ </div>
32
+
33
  ## Prompt template
34
 
35
+
36
  ```
37
 
38
  ```
 
41
 
42
  | Filename | Quant type | File Size | Description |
43
  | -------- | ---------- | --------- | ----------- |
44
+ | [MagicPrompt-Stable-Diffusion-Q2_K.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q2_K.gguf) | Q2_K | 0.076 GB | smallest, significant quality loss - not recommended for most purposes |
45
+ | [MagicPrompt-Stable-Diffusion-Q3_K_S.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q3_K_S.gguf) | Q3_K_S | 0.084 GB | very small, high quality loss |
46
+ | [MagicPrompt-Stable-Diffusion-Q3_K_M.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q3_K_M.gguf) | Q3_K_M | 0.091 GB | very small, high quality loss |
47
+ | [MagicPrompt-Stable-Diffusion-Q3_K_L.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q3_K_L.gguf) | Q3_K_L | 0.095 GB | small, substantial quality loss |
48
+ | [MagicPrompt-Stable-Diffusion-Q4_0.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q4_0.gguf) | Q4_0 | 0.099 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
49
+ | [MagicPrompt-Stable-Diffusion-Q4_K_S.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q4_K_S.gguf) | Q4_K_S | 0.100 GB | small, greater quality loss |
50
+ | [MagicPrompt-Stable-Diffusion-Q4_K_M.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q4_K_M.gguf) | Q4_K_M | 0.105 GB | medium, balanced quality - recommended |
51
+ | [MagicPrompt-Stable-Diffusion-Q5_0.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q5_0.gguf) | Q5_0 | 0.114 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
52
+ | [MagicPrompt-Stable-Diffusion-Q5_K_S.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q5_K_S.gguf) | Q5_K_S | 0.114 GB | large, low quality loss - recommended |
53
+ | [MagicPrompt-Stable-Diffusion-Q5_K_M.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q5_K_M.gguf) | Q5_K_M | 0.118 GB | large, very low quality loss - recommended |
54
+ | [MagicPrompt-Stable-Diffusion-Q6_K.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q6_K.gguf) | Q6_K | 0.129 GB | very large, extremely low quality loss |
55
+ | [MagicPrompt-Stable-Diffusion-Q8_0.gguf](https://huggingface.co/tensorblock/MagicPrompt-Stable-Diffusion-GGUF/blob/main/MagicPrompt-Stable-Diffusion-Q8_0.gguf) | Q8_0 | 0.165 GB | very large, extremely low quality loss - not recommended |
56
 
57
 
58
  ## Downloading instruction