Image-to-Video
Wan2.2
English
remind
remind-5b
video-generation
world-model
video-world-model
causal-video-generation
dynamic-memory
out-of-sight-state-evolution
teaching-video-generators-to-remember
lora
Instructions to use AppliedIntuitionResearch/ReMind with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Wan2.2
How to use AppliedIntuitionResearch/ReMind with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signatured52d3bb -
Polish model card navigation
Verified signaturePromote resource links to badges, use an English prompt example, and remove internal checkpoint-lineage details.a23012d -
Link released Qwen prompt pipeline
Verified signatureReplace the manual prompt-alignment outline with executable CLI instructions from the public release.302e162 -
Document Qwen prompt alignment
Verified signatureAdd the first-frame Qwen3-VL prompt-alignment workflow and mark its documentation complete.a134dae -
Replace DMD EMA with aligned step-480 adapter
Verified signaturePublish checkpoint-1200 EMA from remind-dmd15k-sf4s-a1-b64s4-0919, reproduced with the locked W&B UI-step 480 validation protocol on the TF+2000 base.5bf2930 -
Replace ReMind-5B base with TF+2000 checkpoint
Verified signatureUse the frozen TF checkpoint-2000 base used by the current DMD training line and refresh provenance plus SHA256SUMS.3d15c28
-
Link official ReMind collection
Verified signatureb6c1f90 -
Improve ReMind model discoverability
Verified signature325b5dd -
ReMind-5B model release
0597a2c