nimmusica/nimsmusici-ai 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"In a high fashion editorial shot, nimeta strikes an elegant and simplified pose. She stands tall with one leg slightly forward, allowing a sheer black gown to drape gracefully over her form. The delicate fabric slips off one shoulder before cascading down to pool softly at her feet. One hand gently gathers the material near her hip, conveying effortless poise, while her other arm hangs relaxed at her side. Nimeta head is tilted slightly back and turned to the side, with a soft yet confident gaze that creates an air of quiet allure. The entire scene is bathed in a diffused, glowy light that casts a dreamy, ethereal aura over her silhouette and minimizes harsh shadows, resulting in a luminous and captivating image."
Output
Performance Metrics
11.79s
Prediction Time
11.89s
Total Time
All Input Parameters
{
"image": "https://replicate.delivery/pbxt/NepNJSw1rmLmj4UwCRhZUgcccO8h9GTay0qmBWJsnDCrnmTL/magnifics_upscale-1UdSDHvTXijnZQKfV7gc-IMG_5278.png",
"model": "dev",
"prompt": "In a high fashion editorial shot, nimeta strikes an elegant and simplified pose. She stands tall with one leg slightly forward, allowing a sheer black gown to drape gracefully over her form. The delicate fabric slips off one shoulder before cascading down to pool softly at her feet. One hand gently gathers the material near her hip, conveying effortless poise, while her other arm hangs relaxed at her side. Nimeta head is tilted slightly back and turned to the side, with a soft yet confident gaze that creates an air of quiet allure. The entire scene is bathed in a diffused, glowy light that casts a dreamy, ethereal aura over her silhouette and minimizes harsh shadows, resulting in a luminous and captivating image.",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "png",
"guidance_scale": 3,
"output_quality": 99,
"prompt_strength": 0.73,
"extra_lora_scale": 1,
"num_inference_steps": 28
}
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
free=22595430170624 Downloading weights 2025-09-05T02:58:20Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmprpq4_wnc/weights url=https://replicate.delivery/xezq/HHde8X5oDDWfu0vEXKe7ptye6bbch0razlVX2fMNNPlkRyamC/trained_model.tar 2025-09-05T02:58:20Z | INFO | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local 2025-09-05T02:58:20Z | INFO | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/HHde8X5oDDWfu0vEXKe7ptye6bbch0razlVX2fMNNPlkRyamC/trained_model.tar url=https://replicate.delivery/xezq/HHde8X5oDDWfu0vEXKe7ptye6bbch0razlVX2fMNNPlkRyamC/trained_model.tar 2025-09-05T02:58:20Z | INFO | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/3fc8eb8714d27207e77a6faa3ae2e138ec83dbecf96dfcc3dc409b3c9ad6fb91?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250905%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250905T025820Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=4a2d0f2808da8f5290651b56513c9078756755f665a639f4890a63a8aef05c71 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/HHde8X5oDDWfu0vEXKe7ptye6bbch0razlVX2fMNNPlkRyamC/trained_model.tar 2025-09-05T02:58:21Z | INFO | [ Complete ] dest=/tmp/tmprpq4_wnc/weights size="172 MB" total_elapsed=0.307s url=https://replicate.delivery/xezq/HHde8X5oDDWfu0vEXKe7ptye6bbch0razlVX2fMNNPlkRyamC/trained_model.tar Downloaded weights in 0.37s Loaded LoRAs in 0.93s Using seed: 32838 Prompt: In a high fashion editorial shot, nimeta strikes an elegant and simplified pose. She stands tall with one leg slightly forward, allowing a sheer black gown to drape gracefully over her form. The delicate fabric slips off one shoulder before cascading down to pool softly at her feet. One hand gently gathers the material near her hip, conveying effortless poise, while her other arm hangs relaxed at her side. Nimeta head is tilted slightly back and turned to the side, with a soft yet confident gaze that creates an air of quiet allure. The entire scene is bathed in a diffused, glowy light that casts a dreamy, ethereal aura over her silhouette and minimizes harsh shadows, resulting in a luminous and captivating image. Input image size: 1472x1824 [!] Resizing input image from 1472x1824 to 1168x1440 [!] img2img mode 0%| | 0/21 [00:00<?, ?it/s] 5%|▍ | 1/21 [00:00<00:06, 2.98it/s] 10%|▉ | 2/21 [00:00<00:07, 2.59it/s] 14%|█▍ | 3/21 [00:01<00:07, 2.48it/s] 19%|█▉ | 4/21 [00:01<00:06, 2.44it/s] 24%|██▍ | 5/21 [00:02<00:06, 2.41it/s] 29%|██▊ | 6/21 [00:02<00:06, 2.39it/s] 33%|███▎ | 7/21 [00:02<00:05, 2.38it/s] 38%|███▊ | 8/21 [00:03<00:05, 2.38it/s] 43%|████▎ | 9/21 [00:03<00:05, 2.38it/s] 48%|████▊ | 10/21 [00:04<00:04, 2.37it/s] 52%|█████▏ | 11/21 [00:04<00:04, 2.37it/s] 57%|█████▋ | 12/21 [00:04<00:03, 2.37it/s] 62%|██████▏ | 13/21 [00:05<00:03, 2.36it/s] 67%|██████▋ | 14/21 [00:05<00:02, 2.36it/s] 71%|███████▏ | 15/21 [00:06<00:02, 2.36it/s] 76%|███████▌ | 16/21 [00:06<00:02, 2.36it/s] 81%|████████ | 17/21 [00:07<00:01, 2.36it/s] 86%|████████▌ | 18/21 [00:07<00:01, 2.36it/s] 90%|█████████ | 19/21 [00:07<00:00, 2.36it/s] 95%|█████████▌| 20/21 [00:08<00:00, 2.36it/s] 100%|██████████| 21/21 [00:08<00:00, 2.36it/s] 100%|██████████| 21/21 [00:08<00:00, 2.39it/s] Total safe images: 1 out of 1
Version Details
- Version ID
ae19374e30737bfaa85d760d0e82a6153a640c37bb3721503b7e6ec1186fe315- Version Created
- June 4, 2025