andyx1976/ivograham 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"young man, sim skinny, iivo, slim and skinny, looks at the camera, wearing a wide open dress shirt, revealing his very hairy chest."
Output
Performance Metrics
10.02s
Prediction Time
10.45s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "young man, sim skinny, iivo, slim and skinny, looks at the camera, wearing a wide open dress shirt, revealing his very hairy chest.",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "3:4",
"output_format": "jpg",
"guidance_scale": 3,
"output_quality": 100,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 21
}
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=29365159174144 Downloading weights 2025-02-19T12:30:42Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpgf1rbax9/weights url=https://replicate.delivery/xezq/H7SD8Bfsuw2TSKxkybNqHbPe3TOwEnCz5sjfetfS5mVmSgGiC/trained_model.tar 2025-02-19T12:30:46Z | INFO | [ Complete ] dest=/tmp/tmpgf1rbax9/weights size="215 MB" total_elapsed=3.977s url=https://replicate.delivery/xezq/H7SD8Bfsuw2TSKxkybNqHbPe3TOwEnCz5sjfetfS5mVmSgGiC/trained_model.tar Downloaded weights in 4.00s Loaded LoRAs in 4.56s Using seed: 58313 Prompt: young man, sim skinny, iivo, slim and skinny, looks at the camera, wearing a wide open dress shirt, revealing his very hairy chest. [!] txt2img mode 0%| | 0/21 [00:00<?, ?it/s] 5%|▍ | 1/21 [00:00<00:05, 3.92it/s] 10%|▉ | 2/21 [00:00<00:04, 4.45it/s] 14%|█▍ | 3/21 [00:00<00:04, 4.21it/s] 19%|█▉ | 4/21 [00:00<00:04, 4.12it/s] 24%|██▍ | 5/21 [00:01<00:03, 4.07it/s] 29%|██▊ | 6/21 [00:01<00:03, 4.03it/s] 33%|███▎ | 7/21 [00:01<00:03, 4.02it/s] 38%|███▊ | 8/21 [00:01<00:03, 4.01it/s] 43%|████▎ | 9/21 [00:02<00:02, 4.00it/s] 48%|████▊ | 10/21 [00:02<00:02, 4.00it/s] 52%|█████▏ | 11/21 [00:02<00:02, 3.99it/s] 57%|█████▋ | 12/21 [00:02<00:02, 3.99it/s] 62%|██████▏ | 13/21 [00:03<00:02, 3.98it/s] 67%|██████▋ | 14/21 [00:03<00:01, 3.98it/s] 71%|███████▏ | 15/21 [00:03<00:01, 3.98it/s] 76%|███████▌ | 16/21 [00:03<00:01, 3.98it/s] 81%|████████ | 17/21 [00:04<00:01, 3.98it/s] 86%|████████▌ | 18/21 [00:04<00:00, 3.99it/s] 90%|█████████ | 19/21 [00:04<00:00, 3.99it/s] 95%|█████████▌| 20/21 [00:04<00:00, 3.99it/s] 100%|██████████| 21/21 [00:05<00:00, 3.99it/s] 100%|██████████| 21/21 [00:05<00:00, 4.01it/s] Total safe images: 1 out of 1
Version Details
- Version ID
9705760aa5243423ee6d6d945cc02029de8c7371610e96ca34b810e536c83fb0- Version Created
- February 19, 2025