Views
No views yet

glowing ember linework style to the end of your prompt.| Parameter | Value |
|---|---|
| Trigger | glowing ember linework style |
| Recommended LoRA scale | 1.0 to 1.25 |
| Base model | krea/Krea-2-Turbo |
| Trained on | fal-ai/krea-2-trainer |
1import fal_client
2
3result = fal_client.subscribe(
4 "fal-ai/krea-2/turbo/lora",
5 arguments={
6 "prompt": "a lighthouse on a rocky cliff. glowing ember linework style",
7 "loras": [{"path": "https://huggingface.co/ilkerzgi/krea-2-glowing-ember-linework-lora/resolve/main/glowing-ember-linework.safetensors", "scale": 1.0}],
8 "image_size": {"width": 1024, "height": 1280},
9 },
10)
11print(result["images"][0]["url"])1import { fal } from "@fal-ai/client";
2
3const { data } = await fal.subscribe("fal-ai/krea-2/turbo/lora", {
4 input: {
5 prompt: "a lighthouse on a rocky cliff. glowing ember linework style",
6 loras: [{ path: "https://huggingface.co/ilkerzgi/krea-2-glowing-ember-linework-lora/resolve/main/glowing-ember-linework.safetensors", scale: 1.0 }],
7 image_size: { width: 1024, height: 1280 },
8 },
9});
10console.log(data.images[0].url);fal-ai/krea-2-trainer (100 steps, learning rate 3.5e-4). Train your own style from 4 to 10 reference images:1import fal_client
2
3result = fal_client.subscribe(
4 "fal-ai/krea-2-trainer",
5 arguments={
6 "images_data_url": "https://.../your-dataset.zip",
7 "trigger_phrase": "glowing ember linework style",
8 "steps": 100,
9 "learning_rate": 0.00035,
10 },
11)
12print(result)glowing-ember-linework-comfy.safetensors. It is the
exact same LoRA with the key prefix remapped (base_model.model. to diffusion_model.) so
ComfyUI loads it directly. Download that file into ComfyUI/models/loras/ and use it like
any other LoRA. The original glowing-ember-linework.safetensors is for fal / diffusers.