Did someone say... training? :doro: There's a working lora inside this discussion, trust me.
As description says, its possible to adapt diffusion-pipe to work with Anima, but needs a bit of tinkering, but a rank 32 Lora at 512px batch size 1 uses about 10GB with Qwen Frozen.
The bad news? diffusion-pipe only likes Linux
Here, have the lora 5e-5 AdamW, Batch 2, 512px with buckets
https://drive.google.com/file/d/1ec6YAjx14svK3grwhLfnVOwLrPU_4-zh/view?usp=sharing
Training code: https://github.com/bluvoll/diffusion-pipe runs as usual, added a dataset.toml, and anima.toml as examples.
Model uses 10gb of VRAM at batch size 1, 512px with Qwen Still loaded, gradient checkpointing and bf16
Previews:
NO LORA || LORA pairs.
I'm currently working on having shuffle and keep token working as similarly as it did in Kohya in a personal fork of diffusion-pipe.
More examples
oooor we could nicely ask tdrussell to update diffusion-pipe :P considering he's the creator of both diffusion-pipe and anima
Orrrr we could appreciate the nice gesture, since there’s no official training code, no LoRA support, and not even diffusers compatibility yet.
Besides, there's already a post asking for training code. https://huggingface.co/circlestone-labs/Anima/discussions/10
:3
oooor we could nicely ask tdrussell to update diffusion-pipe :P considering he's the creator of both diffusion-pipe and anima
My post is not meant to replace Tdrussell's code, but rather to help the community experiment with the model getting a hold of basic settings like Learning Rate, and VRAM usage, so we can use his code right out the gate.
oooor we could nicely ask tdrussell to update diffusion-pipe :P considering he's the creator of both diffusion-pipe and anima
My post is not meant to replace Tdrussell's code, but rather to help the community experiment with the model getting a hold of basic settings like Learning Rate, and VRAM usage, so we can use his code right out the gate.
It seems to me that my comment came off pretty antagonistic, sorry, it wasn't meant to come off like that! My intention was just to say that the creator of the model has created training software before, so hopefully we will see some adoption soonish!
oooor we could nicely ask tdrussell to update diffusion-pipe :P considering he's the creator of both diffusion-pipe and anima
My post is not meant to replace Tdrussell's code, but rather to help the community experiment with the model getting a hold of basic settings like Learning Rate, and VRAM usage, so we can use his code right out the gate.
It seems to me that my comment came off pretty antagonistic, sorry, it wasn't meant to come off like that! My intention was just to say that the creator of the model has created training software before, so hopefully we will see some adoption soonish!
Yeah no worries, it just seems that Tdrussell is very busy (perhaps training the model) so I'm just trying to help.
Great work!