Update README.md
Browse files
README.md
CHANGED
|
@@ -84,7 +84,7 @@ This repository holds the [diffusers](https://github.com/huggingface/diffusers)
|
|
| 84 |
|
| 85 |
## Quickstart
|
| 86 |
|
| 87 |
-
|
| 88 |
such as one H200 or B200, or 80 GB with [offloading](#less-gpu-memory).
|
| 89 |
|
| 90 |
```bash
|
|
@@ -317,9 +317,6 @@ unless you have a separate license from MiniMax, and products built on it must s
|
|
| 317 |
encoder's Qwen3-VL-4B parts and the prompt upsampler, based on Qwen3.5-9B, are under the
|
| 318 |
[Apache License 2.0](LICENSE-APACHE). See [NOTICE](NOTICE) for details.
|
| 319 |
|
| 320 |
-
P-H3-Image would not exist without [MiniMax](https://huggingface.co/MiniMaxAI), who released H3 with open weights, and
|
| 321 |
-
the [Qwen team](https://huggingface.co/Qwen).
|
| 322 |
-
|
| 323 |
## What's next?
|
| 324 |
|
| 325 |
- Compress your own models with [Pruna](https://github.com/PrunaAI/pruna) and give us a ⭐️ for more efficiency!
|
|
|
|
| 84 |
|
| 85 |
## Quickstart
|
| 86 |
|
| 87 |
+
Run text-to-image and editing with the same pipeline. At 8 MP in bf16 it needs a GPU with about 101 GB of memory,
|
| 88 |
such as one H200 or B200, or 80 GB with [offloading](#less-gpu-memory).
|
| 89 |
|
| 90 |
```bash
|
|
|
|
| 317 |
encoder's Qwen3-VL-4B parts and the prompt upsampler, based on Qwen3.5-9B, are under the
|
| 318 |
[Apache License 2.0](LICENSE-APACHE). See [NOTICE](NOTICE) for details.
|
| 319 |
|
|
|
|
|
|
|
|
|
|
| 320 |
## What's next?
|
| 321 |
|
| 322 |
- Compress your own models with [Pruna](https://github.com/PrunaAI/pruna) and give us a ⭐️ for more efficiency!
|