monpu7/10liomess 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"
10liomess, depicting Messi standing confidently with the Eiffel Tower directly behind him at night in a distinctly French ambiance. The Eiffel Tower is illuminated and captured in ultra-high definition, showcasing every structural detail in crisp, sharp focus without any blur or softening effects. The iconic lattice design of the tower is clear and vivid, glowing warmly against the Parisian night sky.
Messi is dressed in the official Football Club Barcelona outfit. His expression reflects admiration for the Parisian surroundings, with the clarity of the Eiffel Tower enhancing the depth and allure of the moment. The entire image is focused, capturing each detail from Messi's composed stance to the HD brilliance of the illuminated Eiffel Tower.
"Output
Performance Metrics
9.95s
Prediction Time
10.10s
Total Time
All Input Parameters
{
"model": "dev",
"width": 1440,
"height": 810,
"prompt": "10liomess, depicting Messi standing confidently with the Eiffel Tower directly behind him at night in a distinctly French ambiance. The Eiffel Tower is illuminated and captured in ultra-high definition, showcasing every structural detail in crisp, sharp focus without any blur or softening effects. The iconic lattice design of the tower is clear and vivid, glowing warmly against the Parisian night sky.\n\nMessi is dressed in the official Football Club Barcelona outfit. His expression reflects admiration for the Parisian surroundings, with the clarity of the Eiffel Tower enhancing the depth and allure of the moment. The entire image is focused, capturing each detail from Messi's composed stance to the HD brilliance of the illuminated Eiffel Tower.\n",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "9:16",
"output_format": "png",
"guidance_scale": 3.5,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 30
}
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
2025-01-07 20:59:38.902 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2025-01-07 20:59:38.902 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 91%|█████████ | 277/304 [00:00<00:00, 2758.09it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2718.03it/s] 2025-01-07 20:59:39.014 | SUCCESS | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.11s free=29147873083392 Downloading weights 2025-01-07T20:59:39Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp1vhxdhhu/weights url=https://replicate.delivery/xezq/pmJHlSytDjqmKBfpKrWi3MKe8Jl1Em0qZe0okX9jJVY3ToFoA/trained_model.tar 2025-01-07T20:59:42Z | INFO | [ Complete ] dest=/tmp/tmp1vhxdhhu/weights size="172 MB" total_elapsed=3.016s url=https://replicate.delivery/xezq/pmJHlSytDjqmKBfpKrWi3MKe8Jl1Em0qZe0okX9jJVY3ToFoA/trained_model.tar Downloaded weights in 3.04s 2025-01-07 20:59:42.056 | INFO | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/b648ee29c68e4a5b 2025-01-07 20:59:42.126 | INFO | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded 2025-01-07 20:59:42.126 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2025-01-07 20:59:42.127 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 91%|█████████ | 277/304 [00:00<00:00, 2762.78it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2722.13it/s] 2025-01-07 20:59:42.239 | SUCCESS | fp8.lora_loading:load_lora:539 - LoRA applied in 0.18s Using seed: 30983 0it [00:00, ?it/s] 1it [00:00, 8.45it/s] 2it [00:00, 5.91it/s] 3it [00:00, 5.38it/s] 4it [00:00, 5.17it/s] 5it [00:00, 5.03it/s] 6it [00:01, 4.94it/s] 7it [00:01, 4.91it/s] 8it [00:01, 4.89it/s] 9it [00:01, 4.88it/s] 10it [00:01, 4.86it/s] 11it [00:02, 4.82it/s] 12it [00:02, 4.83it/s] 13it [00:02, 4.83it/s] 14it [00:02, 4.84it/s] 15it [00:03, 4.84it/s] 16it [00:03, 4.83it/s] 17it [00:03, 4.83it/s] 18it [00:03, 4.83it/s] 19it [00:03, 4.82it/s] 20it [00:04, 4.82it/s] 21it [00:04, 4.82it/s] 22it [00:04, 4.81it/s] 23it [00:04, 4.82it/s] 24it [00:04, 4.82it/s] 25it [00:05, 4.83it/s] 26it [00:05, 4.82it/s] 27it [00:05, 4.83it/s] 28it [00:05, 4.83it/s] 29it [00:05, 4.83it/s] 30it [00:06, 4.83it/s] 30it [00:06, 4.90it/s] Total safe images: 1 out of 1
Version Details
- Version ID
1c692de5505b642d820aed4d2631d70d10eb28d14f8982dcf942d976605701d6- Version Created
- January 7, 2025