Flux Dev to Schnell 4 step LoRA - FP32
model_id: flux-dev-to-schnell-4-step-lora-fp32
Model Type: Stable Diffusion
This version is float32 if your card doesn't support BF16 it's better to have this convert to FP16 than BF16. Less precision loss that way.
API Code Snippet
curl --location --request POST 'https://stablediffusionapi.com/api/v4/dreambooth' \
curl --header 'Content-Type: application/json' \
{
"key": "api-key",
"model_id": "flux-dev-to-schnell-4-step-lora-fp32",
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"seed": null,
"guidance_scale": 7.5,
"webhook": null,
"track_id": null
}
No. of images generated
3.95 K
Images
Generated
Images generated with Flux Dev to Schnell 4 step LoRA - FP32 and its prompt