|
Download README.md from xixibuxixi/plot-checkpoints: direct link, hf CLI and curl.
- Browser
- Download file 1 kB
-
https://huggingface.co/xixibuxixi/plot-checkpoints/resolve/main/README.md
- Command line
-
hf download hf://xixibuxixi/plot-checkpoints/README.md
-
curl -L -o README.md https://huggingface.co/xixibuxixi/plot-checkpoints/resolve/main/README.md
1 kB
| # PLOT checkpoints | |
| Private checkpoint repository. Current M3 exploration uses **M3 Simple step 7365**. | |
| - [Current M3 checkpoint, config and training records](m3/m3_simple_fulltrain_player_flow_step7365/README.md) | |
| - Existing M1 checkpoint: `m1/m1_flow_2nodes_b32_eval10k_v2/step_001476000.pt` (unchanged). | |
| - Exact artifact hashes and provenance: [SELECTED.json](SELECTED.json). | |
| M3 step 7365 includes model and optimizer. Pixel VAE and the repaired | |
| fixed_skins_20260917 dataset are required separately. Old M3 step 26000 and the | |
| old step 3300 identity encoder have been removed from the current branch at the | |
| owner's request; historical revisions remain available. Other model repositories, | |
| datasets and training bundles were not changed. | |
| ## M2 and training dependencies | |
| [Complete M2 model and dependency guide](TRAINING_ASSETS.md): Pixel VAE, optional | |
| video backbone, separate vocabularies, latent normalization, and M4 text cache. | |
| M2 and M3 item ID 12 differ; see the guide before coupling them. | |