Downloads · 30 days
65
38% of all-time downloads
lucentcreative/glycor-coralline-type-lora
glycor-coralline-type-lora is a text-to-image model from lucentcreative. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
A FLUX.1-dev LoRA that renders letters and words in an invented material: coralline glyph — a white perforated coral-lattice skeleton wrapped in coral and salmon fronds with dusty pink pom-pom seed heads, lit by god-r…
Downloads · 30 days
65
38% of all-time downloads
All-time downloads
171
Public
Repo size
1 GB
Likes
0
Public
Click a slice to open those files.
.safetensors1 GB · 100%
From the Hugging Face model README
A FLUX.1-dev LoRA that renders letters and words in an invented material: coralline glyph — a white perforated coral-lattice skeleton wrapped in coral and salmon fronds with dusty pink pom-pom seed heads, lit by god-rays over a dark underwater seafloor.
This is the Flux successor to an earlier SDXL experiment; Flux was chosen specifically for its superior letterform and text rendering.
Use the trigger word glycor in the prompt, or at the start of it but paired with the word style.
glycor style, a single letter "g", underwater scene, god rays, dark seafloor background
glycor style. Text that reads "reef",underwater scene, god rays, dark seafloor
The material vocabulary (coral, lattice, pink, fronds) was deliberately excluded from the training captions, so those words remain free at inference and can be added to intensify the look. Because the base is Flux, whole words render legibly — not just single letters.
| Setting | Value |
|---|---|
| Base model | FLUX.1-dev |
| LoRA weight / scale | 0.8 – 1.0 |
| Inference steps | 28 – 35 |
| Guidance (CFG) | 3.5 |
| Sampler | FlowMatch / Euler |
| Resolution | 1024 × 1024 |
Flux uses low guidance (~3.5) and ignores negative prompts — steer entirely through the positive prompt.
Trained 2500 steps, saved every 250. Mid-to-late checkpoints (1000–1750) give the best balance of legibility and material richness.
| Checkpoint | Character |
|---|---|
glycor_v1_000001000 | Clean letters, lighter material |
glycor_v1_000001250 | Balanced |
glycor_v1_000001500 | Richer material, still legible |
glycor_v1 (2500) | Fullest / most detailed |
black-forest-labs/FLUX.1-devFLUX.1-dev LoRAs inherit the FLUX.1-dev Non-Commercial License. See the license link above.
Built with Ostris AI-Toolkit.