fairstonexxx/ai-pes-zs 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"the character is walking the morning forest"
Output
Performance Metrics
29.96s
Prediction Time
29.97s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "the character is walking the morning forest",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 3,
"aspect_ratio": "4:5",
"output_format": "png",
"guidance_scale": 3.5,
"output_quality": 80,
"prompt_strength": 0.85,
"extra_lora_scale": 1,
"num_inference_steps": 32
}
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=26924567511040 Downloading weights 2025-03-27T11:10:02Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpr_4izktz/weights url=https://replicate.delivery/xezq/a0qOiAB1yN5yMZHOqOdtaOQaEJ4eIZUxRrb8bbsnUU3wCUOKA/trained_model.tar 2025-03-27T11:10:06Z | INFO | [ Complete ] dest=/tmp/tmpr_4izktz/weights size="344 MB" total_elapsed=4.291s url=https://replicate.delivery/xezq/a0qOiAB1yN5yMZHOqOdtaOQaEJ4eIZUxRrb8bbsnUU3wCUOKA/trained_model.tar Downloaded weights in 4.32s Loaded LoRAs in 4.94s Using seed: 12410 Prompt: the character is walking the morning forest [!] txt2img mode 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:00<00:21, 1.47it/s] 6%|▋ | 2/32 [00:01<00:18, 1.65it/s] 9%|▉ | 3/32 [00:01<00:18, 1.56it/s] 12%|█▎ | 4/32 [00:02<00:18, 1.52it/s] 16%|█▌ | 5/32 [00:03<00:18, 1.49it/s] 19%|█▉ | 6/32 [00:03<00:17, 1.48it/s] 22%|██▏ | 7/32 [00:04<00:16, 1.47it/s] 25%|██▌ | 8/32 [00:05<00:16, 1.47it/s] 28%|██▊ | 9/32 [00:06<00:15, 1.46it/s] 31%|███▏ | 10/32 [00:06<00:15, 1.46it/s] 34%|███▍ | 11/32 [00:07<00:14, 1.46it/s] 38%|███▊ | 12/32 [00:08<00:13, 1.46it/s] 41%|████ | 13/32 [00:08<00:13, 1.46it/s] 44%|████▍ | 14/32 [00:09<00:12, 1.45it/s] 47%|████▋ | 15/32 [00:10<00:11, 1.45it/s] 50%|█████ | 16/32 [00:10<00:10, 1.45it/s] 53%|█████▎ | 17/32 [00:11<00:10, 1.45it/s] 56%|█████▋ | 18/32 [00:12<00:09, 1.45it/s] 59%|█████▉ | 19/32 [00:12<00:08, 1.45it/s] 62%|██████▎ | 20/32 [00:13<00:08, 1.45it/s] 66%|██████▌ | 21/32 [00:14<00:07, 1.45it/s] 69%|██████▉ | 22/32 [00:14<00:06, 1.45it/s] 72%|███████▏ | 23/32 [00:15<00:06, 1.45it/s] 75%|███████▌ | 24/32 [00:16<00:05, 1.45it/s] 78%|███████▊ | 25/32 [00:17<00:04, 1.45it/s] 81%|████████▏ | 26/32 [00:17<00:04, 1.45it/s] 84%|████████▍ | 27/32 [00:18<00:03, 1.45it/s] 88%|████████▊ | 28/32 [00:19<00:02, 1.45it/s] 91%|█████████ | 29/32 [00:19<00:02, 1.45it/s] 94%|█████████▍| 30/32 [00:20<00:01, 1.45it/s] 97%|█████████▋| 31/32 [00:21<00:00, 1.45it/s] 100%|██████████| 32/32 [00:21<00:00, 1.45it/s] 100%|██████████| 32/32 [00:21<00:00, 1.46it/s] Total safe images: 3 out of 3
Version Details
- Version ID
53582377f9cf70b4102951d1e620e6fa5c6f3d25b94150ace0d8d35e7713db7b- Version Created
- March 27, 2025