delunne/delune 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"Powerful portrait of delune adorned with elaborate jewelry. He wears multiple layered necklaces made of large silver-toned beads and ornate metallic discs, like xerxes in "300" movie, along with an intricate headpiece and nose chain that frames the face. Small white tribal dots are painted on the forehead. The image is a black and white studio photograph with dramatic lighting, emphasizing the textures of the jewelry. Neutral, bright background,.
Keep all details of the face as skin color, hair curly wavy and texture, bring an andregonious vibe for the pose, makeup and jewerly, vogue editorial"
Output
Performance Metrics
41.27s
Prediction Time
41.29s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "Powerful portrait of delune adorned with elaborate jewelry. He wears multiple layered necklaces made of large silver-toned beads and ornate metallic discs, like xerxes in \"300\" movie, along with an intricate headpiece and nose chain that frames the face. Small white tribal dots are painted on the forehead. The image is a black and white studio photograph with dramatic lighting, emphasizing the textures of the jewelry. Neutral, bright background,.\nKeep all details of the face as skin color, hair curly wavy and texture, bring an andregonious vibe for the pose, makeup and jewerly, vogue editorial\n",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 4,
"aspect_ratio": "9:16",
"output_format": "jpg",
"guidance_scale": 4.05,
"output_quality": 100,
"prompt_strength": 0.94,
"extra_lora_scale": 1,
"num_inference_steps": 40
}
Input Parameters
- mask
- Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- seed
- Random seed. Set for reproducible generation
- image
- Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- model
- Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
- width
- Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
- height
- Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
- prompt (required)
- Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.
- go_fast
- Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
- extra_lora
- Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
- lora_scale
- Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
- megapixels
- Approximate number of megapixels for generated image
- num_outputs
- Number of outputs to generate
- aspect_ratio
- Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
- output_format
- Format of the output images
- guidance_scale
- Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
- output_quality
- Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
- prompt_strength
- Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
- extra_lora_scale
- Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
- replicate_weights
- Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
- num_inference_steps
- Number of denoising steps. More steps can give more detailed images, but take longer.
- disable_safety_checker
- Disable safety checker for generated images.
Output Schema
Output
Example Execution Logs
Loaded LoRAs in 2.46s Using seed: 34820 Prompt: Powerful portrait of delune adorned with elaborate jewelry. He wears multiple layered necklaces made of large silver-toned beads and ornate metallic discs, like xerxes in "300" movie, along with an intricate headpiece and nose chain that frames the face. Small white tribal dots are painted on the forehead. The image is a black and white studio photograph with dramatic lighting, emphasizing the textures of the jewelry. Neutral, bright background,. Keep all details of the face as skin color, hair curly wavy and texture, bring an andregonious vibe for the pose, makeup and jewerly, vogue editorial [!] txt2img mode 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:36, 1.06it/s] 5%|▌ | 2/40 [00:01<00:31, 1.19it/s] 8%|▊ | 3/40 [00:02<00:32, 1.12it/s] 10%|█ | 4/40 [00:03<00:32, 1.09it/s] 12%|█▎ | 5/40 [00:04<00:32, 1.08it/s] 15%|█▌ | 6/40 [00:05<00:31, 1.06it/s] 18%|█▊ | 7/40 [00:06<00:31, 1.06it/s] 20%|██ | 8/40 [00:07<00:30, 1.06it/s] 22%|██▎ | 9/40 [00:08<00:29, 1.05it/s] 25%|██▌ | 10/40 [00:09<00:28, 1.05it/s] 28%|██▊ | 11/40 [00:10<00:27, 1.05it/s] 30%|███ | 12/40 [00:11<00:26, 1.05it/s] 32%|███▎ | 13/40 [00:12<00:25, 1.05it/s] 35%|███▌ | 14/40 [00:13<00:24, 1.05it/s] 38%|███▊ | 15/40 [00:14<00:23, 1.05it/s] 40%|████ | 16/40 [00:15<00:22, 1.05it/s] 42%|████▎ | 17/40 [00:16<00:21, 1.05it/s] 45%|████▌ | 18/40 [00:16<00:21, 1.05it/s] 48%|████▊ | 19/40 [00:17<00:20, 1.05it/s] 50%|█████ | 20/40 [00:18<00:19, 1.05it/s] 52%|█████▎ | 21/40 [00:19<00:18, 1.05it/s] 55%|█████▌ | 22/40 [00:20<00:17, 1.05it/s] 57%|█████▊ | 23/40 [00:21<00:16, 1.05it/s] 60%|██████ | 24/40 [00:22<00:15, 1.05it/s] 62%|██████▎ | 25/40 [00:23<00:14, 1.05it/s] 65%|██████▌ | 26/40 [00:24<00:13, 1.05it/s] 68%|██████▊ | 27/40 [00:25<00:12, 1.05it/s] 70%|███████ | 28/40 [00:26<00:11, 1.05it/s] 72%|███████▎ | 29/40 [00:27<00:10, 1.05it/s] 75%|███████▌ | 30/40 [00:28<00:09, 1.05it/s] 78%|███████▊ | 31/40 [00:29<00:08, 1.05it/s] 80%|████████ | 32/40 [00:30<00:07, 1.05it/s] 82%|████████▎ | 33/40 [00:31<00:06, 1.05it/s] 85%|████████▌ | 34/40 [00:32<00:05, 1.05it/s] 88%|████████▊ | 35/40 [00:33<00:04, 1.05it/s] 90%|█████████ | 36/40 [00:34<00:03, 1.05it/s] 92%|█████████▎| 37/40 [00:35<00:02, 1.05it/s] 95%|█████████▌| 38/40 [00:36<00:01, 1.05it/s] 98%|█████████▊| 39/40 [00:37<00:00, 1.05it/s] 100%|██████████| 40/40 [00:38<00:00, 1.05it/s] 100%|██████████| 40/40 [00:38<00:00, 1.05it/s] Total safe images: 4 out of 4
Version Details
- Version ID
311f0b02832e4b6b3092b7f71f71ff678d83dc22d97ed84dc0aa0dafc30b4327- Version Created
- July 12, 2025