mehdiPrunaAI sdiazlor commited on
Commit
9aa003c
·
1 Parent(s): dd9b435

Update README.md (#1)

Browse files

- Update README.md (e58a6c29d607fff0976a6f2e36602ad6185b1fcc)


Co-authored-by: Sara Han Díaz <sdiazlor@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +37 -6
README.md CHANGED
@@ -127,7 +127,7 @@ pipeline and the
127
  [`distilled`](https://github.com/Lightricks/LTX-2/blob/main/packages/ltx-pipelines/src/ltx_pipelines/distilled.py)
128
  pipeline (recommended). (~4 s @ 24 fps)
129
 
130
- <table style="width:100%">
131
  <tr><th>Setting</th><th>Value</th></tr>
132
  <tr><td>Model</td><td>PrunaVAED</td></tr>
133
  <tr><td>Precision</td><td><code>bfloat16</code></td></tr>
@@ -136,7 +136,7 @@ pipeline (recommended). (~4 s @ 24 fps)
136
  <tr><td>Decode</td><td>Full (no tiling / rolling / <code>torch.compile</code>)</td></tr>
137
  </table>
138
 
139
- <table style="width:100%">
140
  <tr>
141
  <th>Clip length</th><th>LTX-2.3 VAED</th><th>PrunaVAED</th><th>Speedup</th>
142
  </tr>
@@ -156,7 +156,7 @@ pipeline (recommended). (~4 s @ 24 fps)
156
 
157
  \* Tiling required on H100; 14533ms otherwise
158
 
159
- <table style="width:100%">
160
  <tr>
161
  <th>Latent set</th><th>Clips</th><th>PSNR ↑</th><th>LPIPS ↓</th><th>SSIM ↑</th><th>Δ-frame PSNR ↑</th>
162
  </tr>
@@ -247,9 +247,40 @@ and commercial terms before using or redistributing the model.
247
  Helper code adapted from Hugging Face diffusers retains its Apache-2.0
248
  attribution; see [`NOTICE`](NOTICE).
249
 
250
- ## Try next
251
 
252
  - **Use PrunaVAED to speed up LTX-2.3 decoding.**
253
- - Try Pruna's end-to-end video models:
 
254
  [P-Video](https://www.pruna.ai/p-video) and
255
- [P-Video documentation](https://docs.pruna.ai/en/stable/docs_pruna_endpoints/performance_models/p-video.html).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
127
  [`distilled`](https://github.com/Lightricks/LTX-2/blob/main/packages/ltx-pipelines/src/ltx_pipelines/distilled.py)
128
  pipeline (recommended). (~4 s @ 24 fps)
129
 
130
+ <table class="w-full table-fixed">
131
  <tr><th>Setting</th><th>Value</th></tr>
132
  <tr><td>Model</td><td>PrunaVAED</td></tr>
133
  <tr><td>Precision</td><td><code>bfloat16</code></td></tr>
 
136
  <tr><td>Decode</td><td>Full (no tiling / rolling / <code>torch.compile</code>)</td></tr>
137
  </table>
138
 
139
+ <table class="w-full table-fixed">
140
  <tr>
141
  <th>Clip length</th><th>LTX-2.3 VAED</th><th>PrunaVAED</th><th>Speedup</th>
142
  </tr>
 
156
 
157
  \* Tiling required on H100; 14533ms otherwise
158
 
159
+ <table class="w-full table-fixed">
160
  <tr>
161
  <th>Latent set</th><th>Clips</th><th>PSNR ↑</th><th>LPIPS ↓</th><th>SSIM ↑</th><th>Δ-frame PSNR ↑</th>
162
  </tr>
 
247
  Helper code adapted from Hugging Face diffusers retains its Apache-2.0
248
  attribution; see [`NOTICE`](NOTICE).
249
 
250
+ ## What's next?
251
 
252
  - **Use PrunaVAED to speed up LTX-2.3 decoding.**
253
+ - Compress your own models with [Pruna](https://github.com/PrunaAI/pruna) and give us a ⭐️ for more efficiency!
254
+ - Want to use our optimized video model right away? Check
255
  [P-Video](https://www.pruna.ai/p-video) and
256
+ [P-Video documentation](https://docs.pruna.ai/en/stable/docs_pruna_endpoints/performance_models/p-video.html).
257
+
258
+ <style>
259
+ .model-button {
260
+ display: inline-flex;
261
+ flex-direction: row;
262
+ justify-content: center;
263
+ align-items: center;
264
+ gap: 8px;
265
+
266
+ padding: 8px 20px;
267
+ border: none;
268
+ border-radius: 8px;
269
+
270
+ background: #9334e9;
271
+ color: #ffffff;
272
+
273
+ font-size: 14px;
274
+ font-weight: 400;
275
+ line-height: 1;
276
+ text-decoration: none;
277
+ white-space: nowrap;
278
+ cursor: pointer;
279
+
280
+ box-sizing: border-box;
281
+ overflow: visible;
282
+ opacity: 1;
283
+ }
284
+ </style>
285
+
286
+ <a href="https://dashboard.pruna.ai/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=hf_traffic" class="model-button">Try our models</a>