Card: region head coming, LoRA run stopped at step 500
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ tags:
|
|
| 14 |
# MiniMax H3 two-track mixed resolution (MPEG-Diffusion)
|
| 15 |
|
| 16 |
> [!WARNING]
|
| 17 |
-
> **Research weights, help wanted.** The
|
| 18 |
|
| 19 |
> [!CAUTION]
|
| 20 |
> **License and territory.** Derived from MiniMax H3 under the [MiniMax H3 Community License Agreement](LICENSE) (see [`NOTICE`](NOTICE)). Use and redistribution are allowed **only outside the European Union, the United Kingdom, the Republic of Korea and the United States of America**. Commercial use above US$20M yearly revenue needs MiniMax's written authorization. Do not use these weights to impersonate anyone, and disclose machine-generated output.
|
|
@@ -25,7 +25,8 @@ How it works: the unmodified H3 renders the whole frame at half resolution. A re
|
|
| 25 |
|
| 26 |
| Folder | What |
|
| 27 |
|---|---|
|
| 28 |
-
| [`
|
|
|
|
| 29 |
|
| 30 |
- Code, sampler and training pipeline: [scrya-com/mpeg-diffusion](https://github.com/scrya-com/mpeg-diffusion) (`lot/two_track_h3.py`, `lot/train_tt.py`, one command: `lot/train_tt_all.sh`).
|
| 31 |
- Precomputed caption embeddings for the Pexels photos, which skip the 32B text encoder: [johndpope/MiniMax-H3-pexels-people-text](https://huggingface.co/datasets/johndpope/MiniMax-H3-pexels-people-text).
|
|
|
|
| 14 |
# MiniMax H3 two-track mixed resolution (MPEG-Diffusion)
|
| 15 |
|
| 16 |
> [!WARNING]
|
| 17 |
+
> **Research weights, help wanted.** The region head is published once its current run finishes. The LoRA is not published yet: its first run was stopped at step 500 to free the GPU for the region head. There is no image-quality result yet. Faces from the untrained sampler stay at half-resolution quality and can come out distorted. Training is meant to fix that. Help and results: [scrya-com/mpeg-diffusion issue #2](https://github.com/scrya-com/mpeg-diffusion/issues/2).
|
| 18 |
|
| 19 |
> [!CAUTION]
|
| 20 |
> **License and territory.** Derived from MiniMax H3 under the [MiniMax H3 Community License Agreement](LICENSE) (see [`NOTICE`](NOTICE)). Use and redistribution are allowed **only outside the European Union, the United Kingdom, the Republic of Korea and the United States of America**. Commercial use above US$20M yearly revenue needs MiniMax's written authorization. Do not use these weights to impersonate anyone, and disclose machine-generated output.
|
|
|
|
| 25 |
|
| 26 |
| Folder | What |
|
| 27 |
|---|---|
|
| 28 |
+
| [`region_head/`](region_head) | The self-selected region head: one linear layer on block 25 of the frozen DiT that marks the subject partway through sampling, and so sets the full-resolution region and the Level-of-Token layout. Trained on 2,354 pictures with YOLOE subject labels. Its card has the held-out mIoU and the limits. Uploaded when training finishes. |
|
| 29 |
+
| LoRA (not published) | Lets the full-resolution track start earlier. First run (2,346 pairs, RTX 5090) stopped at step 500 with held-out loss down 21% (half resolution) and 26% (full resolution). |
|
| 30 |
|
| 31 |
- Code, sampler and training pipeline: [scrya-com/mpeg-diffusion](https://github.com/scrya-com/mpeg-diffusion) (`lot/two_track_h3.py`, `lot/train_tt.py`, one command: `lot/train_tt_all.sh`).
|
| 32 |
- Precomputed caption embeddings for the Pexels photos, which skip the 32B text encoder: [johndpope/MiniMax-H3-pexels-people-text](https://huggingface.co/datasets/johndpope/MiniMax-H3-pexels-people-text).
|