<h2 id="hunyuanvideo-lora-mhfpq3pjc">HunyuanVideo LoRA</h2>This can generate fluid art styled animations, trigger words are <code>flu1dart</code> and <code>in a fluidart style</code>. Tested at weights between 0.8 and 1.0.Example Prompt:<pre><code>(neon glow melting over a planet like saturn, galactic explosions behind the flaming crescent backlit, in a fluidart style, flu1dart)

beautiful combination of multiple colors, green yellow red blue amber all glowing in streaks like a complex woodgrain pattern or layers of a planet like Jupiter, fluid art mixtures and radiant colors fast moving liquid</code></pre>Trained with <a target="_blank" rel="ugc" href="https://github.com/tdrussell/diffusion-pipe/">https://github.com/tdrussell/diffusion-pipe/</a>, using the same image dataset as the one for the Fluid Art Flux LoRA.<h2 id="flux-lora-qsaq3tt54">flux LoRA</h2>Alternative versions trained at different steps are available and may produce different results, v1's at 1800 steps works very well at higher strengths.v1.1 works with Schnell and Dev. Tested on latest ComfyUI &amp; Forge.Article with ComfyUI workflow &amp; training information: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/6706">https://civarchive.com/articles/6706</a>

Fluid Art LoRA

Improved captioning and learning rate to improve quality. Seems to work with Schnell as well. Try out the 2200 step version out, it may improve quality. Still testing between the two.NOTE: Trigger word changed to more unique token "<code>flu1dart</code>"

Files with SHA256: 3dfb425c196c2713fc58cdfa1d79b815dc6ced729c196bad50142e40d5a84b4f