39 7 13

araminta_k PRO

alvdansen

https://bento.me/araminta-k

Araminta_k

AI & ML interests

Finetuning LoRA Models and ComfyUI Workflows. If you want to use my LoRAs commercially, please reach out!

Recent Activity

liked a dataset 2 days ago

NousResearch/Hermes-3-Dataset

liked a dataset 2 days ago

UESTC-BICS/I2E

posted an update 4 days ago

Releasing Flimmer today — a video LoRA training toolkit for WAN 2.1 and 2.2 that covers the full pipeline from raw footage to trained checkpoint. The standout feature is phased training: multi-stage runs where each phase has its own learning rate, epochs, and dataset, with the checkpoint carrying forward automatically. Built specifically with WAN 2.2's dual-expert MoE architecture in mind. Data prep tools are standalone and output standard formats — they work with any trainer, not just Flimmer. Early release, building in the open. LTX support coming next. http://github.com/alvdansen/flimmer-trainer

View all activity

Organizations

liked 2 datasets 2 days ago

NousResearch/Hermes-3-Dataset

Viewer • Updated Jul 11, 2025 • 959k • 841 • 300

UESTC-BICS/I2E

Viewer • Updated Jan 17 • 1.69M • 640 • 4

posted an update 4 days ago

Post

1197

Releasing Flimmer today — a video LoRA training toolkit for WAN 2.1 and 2.2 that covers the full pipeline from raw footage to trained checkpoint.
The standout feature is phased training: multi-stage runs where each phase has its own learning rate, epochs, and dataset, with the checkpoint carrying forward automatically. Built specifically with WAN 2.2's dual-expert MoE architecture in mind.

Data prep tools are standalone and output standard formats — they work with any trainer, not just Flimmer.

Early release, building in the open. LTX support coming next.

http://github.com/alvdansen/flimmer-trainer

updated a model 4 days ago

alvdansen/flimmer-trainer

Image-to-Video • Updated 4 days ago • 1

published a model 4 days ago

alvdansen/flimmer-trainer

Image-to-Video • Updated 4 days ago • 1

replied to their post 18 days ago

Thank you!!

posted an update 18 days ago

Post

1837

Just open-sourced LoRA Gym with Timothy - production-ready training pipeline for character, motion, aesthetic, and style LoRAs on Wan 2.1/2.2, built on musubi-tuner.

16 training templates across Modal (serverless) and RunPod (bare metal) covering T2V, I2V, Lightning-merged, and vanilla variants.

Our current experimentation focus is Wan 2.2, which is why we built on musubi-tuner (kohya-ss). Wan 2.2's DiT uses a Mixture-of-Experts architecture with two separate experts gated by a hard timestep switch - you're training two LoRAs per concept, one for high-noise (composition/motion) and one for low-noise (texture/identity), and loading both at inference. Musubi handles this dual-expert training natively, and our templates build on top of it to manage the correct timestep boundaries, precision settings, and flow shift values so you don't have to debug those yourself. We've also documented bug fixes for undocumented issues in musubi-tuner and validated hyperparameter defaults derived from cross-referencing multiple practitioners' results rather than untested community defaults.

Also releasing our auto-captioning toolkit for the first time. Per-LoRA-type captioning strategies for characters, styles, motion, and objects. Gemini (free) or Replicate backends.

Current hyperparameters reflect consolidated community findings. We've started our own refinement and plan to release specific recommendations and methodology as soon as next week.

Repo: github.com/alvdansen/lora-gym

2 replies

updated a model 6 months ago

alvdansen/upload-models

Updated Aug 27, 2025

published a model about 1 year ago

Collection

This collection features awesome opensource LoRAs trained by members of the Glif Community during Loradex Early Access! • 14 items • Updated Oct 18, 2024 • 19

updated a model over 1 year ago

glif/ClayDay

Text-to-Image • Updated Sep 24, 2024 • 15 • • 5

araminta_k PRO

AI & ML interests

Recent Activity

Organizations

alvdansen's activity