swk23/padmelive 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"tok , A close-up of a woman wearing a flowing blue dress, rasing her fist. fist pumping"
Output
Performance Metrics
11.44s
Prediction Time
11.57s
Total Time
All Input Parameters
{
"image": "https://replicate.delivery/pbxt/MVmTAJ4xeb8tsK30nfjCb3WBKkiwoNLJndJuKEJDLZgEvIKi/479160428_644521281390082_3747235023009175098_n.jpg",
"model": "dev",
"prompt": "tok , A close-up of a woman wearing a flowing blue dress, rasing her fist. fist pumping",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "21:9",
"output_format": "jpg",
"guidance_scale": 3,
"output_quality": 80,
"prompt_strength": 0.8,
"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
Loaded LoRAs in 2.49s Using seed: 61043 Prompt: tok , A close-up of a woman wearing a flowing blue dress, rasing her fist. fist pumping Input image size: 2048x1536 [!] Resizing input image from 2048x1536 to 1440x1088 [!] img2img mode 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:06, 3.44it/s] 9%|▊ | 2/23 [00:00<00:07, 3.00it/s] 13%|█▎ | 3/23 [00:01<00:06, 2.86it/s] 17%|█▋ | 4/23 [00:01<00:06, 2.81it/s] 22%|██▏ | 5/23 [00:01<00:06, 2.78it/s] 26%|██▌ | 6/23 [00:02<00:06, 2.76it/s] 30%|███ | 7/23 [00:02<00:05, 2.75it/s] 35%|███▍ | 8/23 [00:02<00:05, 2.74it/s] 39%|███▉ | 9/23 [00:03<00:05, 2.73it/s] 43%|████▎ | 10/23 [00:03<00:04, 2.73it/s] 48%|████▊ | 11/23 [00:03<00:04, 2.73it/s] 52%|█████▏ | 12/23 [00:04<00:04, 2.73it/s] 57%|█████▋ | 13/23 [00:04<00:03, 2.73it/s] 61%|██████ | 14/23 [00:05<00:03, 2.72it/s] 65%|██████▌ | 15/23 [00:05<00:02, 2.73it/s] 70%|██████▉ | 16/23 [00:05<00:02, 2.73it/s] 74%|███████▍ | 17/23 [00:06<00:02, 2.72it/s] 78%|███████▊ | 18/23 [00:06<00:01, 2.72it/s] 83%|████████▎ | 19/23 [00:06<00:01, 2.73it/s] 87%|████████▋ | 20/23 [00:07<00:01, 2.73it/s] 91%|█████████▏| 21/23 [00:07<00:00, 2.73it/s] 96%|█████████▌| 22/23 [00:07<00:00, 2.73it/s] 100%|██████████| 23/23 [00:08<00:00, 2.72it/s] 100%|██████████| 23/23 [00:08<00:00, 2.75it/s] Total safe images: 1 out of 1
Version Details
- Version ID
cfce21225cd3c64a5558efe7577367f5ab8e57b99e4700d0e1baba1954ba144e- Version Created
- January 24, 2025