ad-ams/lanota-cap 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"In a modern, sleek gym environment filled with state-of-the-art equipment, the focal point is a sophisticated, white cubic LNOTA aroma diffuser. Positioned on a polished wooden shelf near the entrance, the LNOTA complements the gym's minimalist design and welcomes visitors with its elegant presence. The diffuser's matte surface is highlighted by the bright overhead LED lights, which give the setting a crisp, clean look. Surrounding the shelf, there are neatly organized workout towels and a small potted plant, adding a touch of freshness. The gym features large, floor-to-ceiling windows along one side, allowing natural light to flood the space and giving a view of the vibrant cityscape outside. The flooring is a mix of sleek black rubber and polished hardwood, enhancing the modern and professional atmosphere. Posters of motivational quotes in bold typography adorn the walls, maintaining a focus on wellness and performance. The overall composition showcases a sense of energy and vitality, with the LNOTA diffuser adding a calm yet stylish touch to the dynamic gym setting."
Output
Performance Metrics
22.24s
Prediction Time
25.36s
Total Time
All Input Parameters
{
"model": "dev",
"width": 1024,
"height": 1024,
"prompt": "In a modern, sleek gym environment filled with state-of-the-art equipment, the focal point is a sophisticated, white cubic LNOTA aroma diffuser. Positioned on a polished wooden shelf near the entrance, the LNOTA complements the gym's minimalist design and welcomes visitors with its elegant presence. The diffuser's matte surface is highlighted by the bright overhead LED lights, which give the setting a crisp, clean look. Surrounding the shelf, there are neatly organized workout towels and a small potted plant, adding a touch of freshness. The gym features large, floor-to-ceiling windows along one side, allowing natural light to flood the space and giving a view of the vibrant cityscape outside. The flooring is a mix of sleek black rubber and polished hardwood, enhancing the modern and professional atmosphere. Posters of motivational quotes in bold typography adorn the walls, maintaining a focus on wellness and performance. The overall composition showcases a sense of energy and vitality, with the LNOTA diffuser adding a calm yet stylish touch to the dynamic gym setting.",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 2,
"aspect_ratio": "1:1",
"output_format": "png",
"guidance_scale": 3,
"output_quality": 80,
"prompt_strength": 0.8,
"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
2024-11-29 11:49:41.193 | DEBUG | fp8.lora_loading:apply_lora_to_model:569 - Extracting keys 2024-11-29 11:49:41.193 | DEBUG | fp8.lora_loading:apply_lora_to_model:576 - Keys extracted Applying LoRA: 0%| | 0/13 [00:00<?, ?it/s] Applying LoRA: 100%|██████████| 13/13 [00:00<00:00, 12727.81it/s] 2024-11-29 11:49:41.195 | SUCCESS | fp8.lora_loading:unload_loras:559 - LoRAs unloaded in 0.0015s free=6311284187136 Downloading weights 2024-11-29T11:49:41Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpug7sijf_/weights url=https://replicate.delivery/yhqm/FeEMofzjEjhXqUOZmTkag6iDYpj5gBdHf0TXDniMNI95p08mA/trained_model.tar 2024-11-29T11:49:43Z | INFO | [ Complete ] dest=/tmp/tmpug7sijf_/weights size="172 MB" total_elapsed=2.212s url=https://replicate.delivery/yhqm/FeEMofzjEjhXqUOZmTkag6iDYpj5gBdHf0TXDniMNI95p08mA/trained_model.tar Downloaded weights in 2.24s 2024-11-29 11:49:43.431 | INFO | fp8.lora_loading:convert_lora_weights:493 - Loading LoRA weights for /src/weights-cache/09770438e14fdb89 2024-11-29 11:49:43.508 | INFO | fp8.lora_loading:convert_lora_weights:514 - LoRA weights loaded 2024-11-29 11:49:43.508 | DEBUG | fp8.lora_loading:apply_lora_to_model:569 - Extracting keys 2024-11-29 11:49:43.509 | DEBUG | fp8.lora_loading:apply_lora_to_model:576 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 91%|█████████ | 277/304 [00:00<00:00, 2756.77it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2688.87it/s] 2024-11-29 11:49:43.622 | SUCCESS | fp8.lora_loading:load_lora:534 - LoRA applied in 0.19s Using seed: 28107 0it [00:00, ?it/s] 1it [00:00, 8.33it/s] 2it [00:00, 5.83it/s] 3it [00:00, 5.31it/s] 4it [00:00, 5.08it/s] 5it [00:00, 4.98it/s] 6it [00:01, 4.89it/s] 7it [00:01, 4.86it/s] 8it [00:01, 4.84it/s] 9it [00:01, 4.82it/s] 10it [00:02, 4.81it/s] 11it [00:02, 4.80it/s] 12it [00:02, 4.80it/s] 13it [00:02, 4.79it/s] 14it [00:02, 4.80it/s] 15it [00:03, 4.79it/s] 16it [00:03, 4.79it/s] 17it [00:03, 4.79it/s] 18it [00:03, 4.79it/s] 19it [00:03, 4.79it/s] 20it [00:04, 4.79it/s] 21it [00:04, 4.79it/s] 22it [00:04, 4.79it/s] 23it [00:04, 4.79it/s] 24it [00:04, 4.79it/s] 25it [00:05, 4.79it/s] 26it [00:05, 4.79it/s] 27it [00:05, 4.79it/s] 28it [00:05, 4.79it/s] 29it [00:05, 4.79it/s] 30it [00:06, 4.79it/s] 31it [00:06, 4.78it/s] 32it [00:06, 4.78it/s] 33it [00:06, 4.78it/s] 34it [00:07, 4.78it/s] 35it [00:07, 4.77it/s] 36it [00:07, 4.77it/s] 37it [00:07, 4.78it/s] 38it [00:07, 4.78it/s] 39it [00:08, 4.78it/s] 40it [00:08, 4.77it/s] 40it [00:08, 4.84it/s] 0it [00:00, ?it/s] 1it [00:00, 4.80it/s] 2it [00:00, 4.79it/s] 3it [00:00, 4.79it/s] 4it [00:00, 4.78it/s] 5it [00:01, 4.76it/s] 6it [00:01, 4.77it/s] 7it [00:01, 4.78it/s] 8it [00:01, 4.78it/s] 9it [00:01, 4.78it/s] 10it [00:02, 4.78it/s] 11it [00:02, 4.77it/s] 12it [00:02, 4.77it/s] 13it [00:02, 4.77it/s] 14it [00:02, 4.77it/s] 15it [00:03, 4.77it/s] 16it [00:03, 4.77it/s] 17it [00:03, 4.77it/s] 18it [00:03, 4.77it/s] 19it [00:03, 4.77it/s] 20it [00:04, 4.77it/s] 21it [00:04, 4.77it/s] 22it [00:04, 4.77it/s] 23it [00:04, 4.78it/s] 24it [00:05, 4.78it/s] 25it [00:05, 4.78it/s] 26it [00:05, 4.78it/s] 27it [00:05, 4.78it/s] 28it [00:05, 4.79it/s] 29it [00:06, 4.78it/s] 30it [00:06, 4.78it/s] 31it [00:06, 4.78it/s] 32it [00:06, 4.78it/s] 33it [00:06, 4.78it/s] 34it [00:07, 4.78it/s] 35it [00:07, 4.78it/s] 36it [00:07, 4.78it/s] 37it [00:07, 4.78it/s] 38it [00:07, 4.78it/s] 39it [00:08, 4.78it/s] 40it [00:08, 4.78it/s] 40it [00:08, 4.78it/s] Total safe images: 2 out of 2
Version Details
- Version ID
a2898a5567be30f10a2a7a60d30e5f9ee08e4ee1379967894d645e9958c4be43- Version Created
- September 19, 2024