Flux LoRA
AI generationBlack Forest LabsFlux Dev with custom LoRA support. Paste a LoRA URL to apply styles, characters, or concepts.
- Runs
- On our servers
- Typical time
- 5-15s
- Inputs
- 2
- Outputs
- 1
Inputs
| Port | Type | ID |
|---|---|---|
| Prompt | text | prompt-in |
| Imageoptional | image | image-in |
Outputs
| Port | Type | ID |
|---|---|---|
| Image | image | image-out |
Settings
| Setting | Type | Default | Options |
|---|---|---|---|
| LoRA URLCivitAI or HuggingFace .safetensors link | text | - | |
| LoRA StrengthHow strongly the LoRA style is applied | slider | 0.8 | 0.1 to 1.5 |
| TransformationHow much the image changes from the original. Only applies when an image is connected. | slider | 0.75 | 0.1 to 1 |
| Aspect RatioOutput shape | select | 1:1 | 1:1 Square, 16:9 Landscape, 9:16 Portrait, 4:3 Standard |
| StepsMore steps = finer detail, slower render | slider | 28 | 1 to 50 |
| GuidanceHow closely the result follows your prompt | slider | 3.5 | 1 to 20 |
| SeedFixed number for reproducible results, 0 = random | number | 0 | 0 to 2147483647 |
Prompting
Describe your image...
Maximum prompt length: 2000 characters.
What this connects into (24)
Computed from the port compatibility rules, so it stays correct as nodes change.
- Nano Banana 2
- Nano Banana Pro
- GPT Image 2
- Gemini Omni
- Seedance 2.0
- Grok Imagine 1.5 I2V
- Kling 3.0 I2V
- Kling 3.0 Pro I2V
- Kling O3 I2V
- Kling O1 FLF2V
- WAN 2.7 I2V
- HappyHorse 1.0 I2V
- WAN Pro I2V
- WAN Effects
- Seedance 2.0 I2V
- Vidu Q1 FLF2V
- Kling O3 Reference
- Kling O1 Reference
- Seedance 2.0 Reference
- Hyper3D Rodin
- Hunyuan3D v3
- Trellis
- SHARP Gaussian
- Clarity Upscaler
Node ID flux-lora. Open it in Studio with Tab, then type the name.