Flat Color - Style
Trained on images without visible lineart, flat colors, and little to no indication of depth.
ℹ️ LoRA work best when applied to the base models on which they are trained. Please read the About This Version on the appropriate base models and workflow/training information.
This is a small style LoRA I thought would be interesting to try with a v-pred model (noobai v-pred), for the reduced color bleeding and strong blacks in particular.
The effect is quite nice and easy to evaluate in training, so I've extended the dataset with videos in following versions for text-to-video models like Wan and Hunyuan, and it is what I am generally using to test LoRA training on new models now.
Recommended tags:
flat color, no lineart, blending, negative space, {{color}} backgroundDescription
[WAN 14B] LoRA
Trained with diffusion-pipe on Wan2.1-T2V-14B with the same config as the v2.0 [hunyuan] version
Seems usable for both text-to-video and image-to-video workflows with Wan
Text to Video previews generated with ComfyUI_examples/wan/#text-to-video
Loading the LoRA with LoraLoaderModelOnly node and using the fp8 14B wan2.1_t2v_14B_fp8_e4m3fn.safetensors
* it is recommended to use the newer scaled fp8 14B wan2.1_t2v_14B_fp8_scaled.safetensors
Image to Video previews generated with ComfyUI_examples/wan/#image-to-video
Using image generations from the IL/Noobai versions of this model card
FAQ
Comments (8)
That's awesome, is the training script for the wan model's lora available now? Is there a tutorial yet?
Yes available in diffusion-pipe: https://github.com/tdrussell/diffusion-pipe/blob/main/docs/supported_models.md#wan21
Don't think the best settings are known for Wan yet.
I've only updated the config.toml [model] config from the Hunyuan training for this test that I thought worked well enough.
Converting the videos to 16fps matching the Wan arch would be probably be better - will see!
@motimalu Thanks for the reply, I'll give it a try!
Thank you so so much!
Hello, you can check the "About this version" section for each versions training details
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.