Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

None defined yet.
alvdansen 
posted an update 9 days ago
view post
Post
1238
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
alvdansen 
posted an update 23 days ago
view post
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
·
alvdansen 
posted an update over 1 year ago
view post
Post
5267
📸Photo LoRA Drop📸

I've been working on this one for a few days, but really I've had this dataset for a few years! I collected a bunch of open access photos online back in late 2022, but I was never happy enough with how they played with the base model!

I am so thrilled that they look so nice with Flux!

This for me is a version one of this model - I still see room for improvement and possibly expansion of it's 40 image dataset. For those who are curious:

40 Image
3200 Steps
Dim 32
3e-4

Enjoy! Create! Big thank you to Glif for sponsoring the model creation! :D

alvdansen/flux_film_foto
alvdansen 
posted an update over 1 year ago
view post
Post
7332
Alright Ya'll

I know it's a Saturday, but I decided to release my first Flux Dev Lora.

A retrain of my "Frosting Lane" model and I am sure the styles will just keep improving.

Have fun! Link Below - Thanks again to @ostris for the trainer and Black Forest Labs for the awesome model!

alvdansen/frosting_lane_flux
alvdansen 
posted an update over 1 year ago
view post
Post
4673
New model drop...🥁

FROSTING LANE REDUX

The v1 of this model was released during a big model push, so I think it got lost in the shuffle. I revisited it for a project and realized it wasn't inventive enough around certain concepts, so I decided to retrain.

alvdansen/frosting_lane_redux

I think the original model was really strong on it's own, but because it was trained on fewer images I found that it was producing a very lackluster range of facial expressions, so I wanted to improve that.

The hardest part of creating models like this, I find, is maintaining the detailed linework without without overfitting. It takes a really balanced dataset and I repeat the data 12 times during the process, stopping at the last 10-20 epochs.

It is very difficult to predict the exact amount of time needed, so for me it is crucial to do epoch stops. Every model has a different threshold for ideal success.
alvdansen 
posted an update over 1 year ago
view post
Post
3024
I really like what the @jasperAITeam designed with Flash LoRA. It works really well for something that generates so quickly, and I'm excited to test it out with Animate Diff, because I recently was testing LCM on it's own for AD and the results were already promising.

I put together my own page of models using their code and LoRA. Enjoy!

alvdansen/flash-lora-araminta-k-styles
alvdansen 
posted an update over 1 year ago
alvdansen 
posted an update over 1 year ago
view post
Post
5925
New LoRA Model!

I trained this model on a new spot I'm really excited to share (soon!)

This Monday I will be posting my first beginning to end blog showing the tool I've used, dataset, captioning techniques, and parameters to finetune this LoRA.

For now, check out the model in the link below.

alvdansen/m3lt
·
alvdansen 
posted an update over 1 year ago
view post
Post
2612
Per popular request, I'm working on a beginning to end LoRA training workflow blog for a style.

It will focus on dataset curation through training on a pre-determined style to give a better insight on my process.

Curious what are some questions you might have that I can try to answer in it?
alvdansen 
posted an update over 1 year ago
view post
Post
2482
A few new styles added as SDXL LoRA:

Midsommar Cartoon
A playful cartoon style featuring bold colors and a retro aesthetic. Personal favorite at the moment.
alvdansen/midsommarcartoon
---
Wood Block XL
I've started training public domain styles to create some interesting datasets. In this case I found a group of images taken from really beautiful and colorful Japanese Blockprints.
alvdansen/wood-block-xl
--
Dimension W
For this model I did actually end up working on an SD 1.5 model as well as an SDXL. I prefer the SDXL version, and I am still looking for parameters I am really happy with for SD 1.5. That said, both have their merits. I trained this with the short film I am working on in mind.
alvdansen/dimension-w
alvdansen/dimension-w-sd15
alvdansen 
posted an update over 1 year ago
view post
Post
994
Hey all!

Here I take a somewhat strong stance and am petitioning to revisit the default training parameters on the Diffusers LoRA page.

In my opinion and after observing and testing may training pipelines shared by startups and resources, I have found that many of them exhibit the same types of issues. Upon discussing with some of these founders and creators, the common theme has been working backwards from the Diffusers LoRA page.

In this article, I explain why the defaults in the Diffuser LoRA code produce some positive results, which can be initially misleading, and a suggestion on how that could be improved.

https://huggingface.co/blog/alvdansen/revisit-diffusers-default-params
  • 4 replies
·
alvdansen 
posted an update over 1 year ago
view post
Post
3258
Hey All!

I've been asked a lot of share more on how I train LoRAs. The truth is I don't think my advice is very helpful without also including more contextual, theoretical commentary on how I **think** about training LoRAs for SDXL and other models.

I wrote a first article here about it - let me know what you think.

https://huggingface.co/blog/alvdansen/thoughts-on-lora-training-1

Edit: Also people kept asking where to start so I made a list of possible resources:
https://huggingface.co/blog/alvdansen/thoughts-on-lora-training-pt-2-training-services
·
alvdansen 
posted an update over 1 year ago
view post
Post
6939
I had a backlog of LoRA model weights for SDXL that I decided to prioritize this weekend and publish. I know many are using SD3 right now, however if you have the time to try them, I hope you enjoy them.

I intend to start writing more fully on the thought process behind my approach to curating and training style and subject finetuning, beginning this next week.

Thank you for reading this post! You can find the models on my page and I'll drop a few previews here.
·