Organic Fill Random 🎲

Eden_OrganicFillRandom is the "roll the dice" version of the pack's organic fill animation. Instead of exposing the twenty knobs that Eden_OrganicFillAnimation hands you, it samples them all randomly from ranges the Eden team found produce good results, then runs the same growth simulation. You set a seed, you get a fill animation - and you have no idea until it renders what shape the growth will take.

How it works

The node uses your seed to drive a Python RNG and a NumPy RNG, then samples every internal parameter from tuned ranges: target_size from {512, 512, 768}, threshold_value from 80–192, seed_radius 3–10, growth_threshold 0.3–0.8, noise ranges from a hand-picked set of six bands, starting_position from all ten options, invert_input from a weighted choice (three true, one false), num_seeds 1–2, and color_channel weighted toward random and red. Then it runs the same organic-fill simulation as its parameterized sibling and produces frames.

The second output is where this node gets interesting for reproducibility: params_info, a string reporting exactly what got sampled - target size, threshold, seed radius, growth threshold, noise range, position, and so on. If you get an animation you love, read that string, feed the values into Eden_OrganicFillAnimation as explicit parameters, and lock it down.

Inputs

• image (IMAGE) - the input.
• target_seconds (default 24, 0.5–120) - duration.
• seed - the whole variety comes from this one number.
• fps (default 24) and loop (default true) - video shape.

Outputs: frames (IMAGE) and params_info (STRING).

When to use it

This is a variety generator, and that's a feature for certain jobs. If you're building an animation loop reel or a batch of transition options and you want breadth fast, chain this node with several seeds and pick. It's also the better default when you don't have a strong opinion about the exact growth behavior - the sampled ranges are biased toward "looks good," which is more than most of us would manage picking blind. When you find one you like, the params_info → explicit-node round trip is a clean handoff.

Installing it

Part of the Eden.art nodesuite. Install via ComfyUI Manager (search "Eden.art nodesuite") or git clone https://github.com/edenartlab/eden_comfy_pipelines into custom_nodes/, then pip install -r requirements.txt and restart.

Common issues

The obvious one: with randomness this broad, some seeds produce duds - a stalled fill or a nearly-empty result. Don't fight it; change the seed. Also remember frames is a batch of images, not a video file - encode it downstream. And the default target_seconds is 24 (vs 5 on the explicit node), so expect a longer render and a bigger frame batch out of the box. If memory is a concern, drop fps or the duration.