adellcox/sage-v1-fresh 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"sage, same face style and proportions as reference. Gentle natural smile showing a few upper teeth, purple hair, glasses, purple heart on shirt.
--no extra hands, no distortion, no watermark, no misaligned eyes"
Output
Performance Metrics
7.03s
Prediction Time
8.87s
Total Time
All Input Parameters
{
"image": "https://replicate.delivery/pbxt/NcJikP7aGhZOeYnRXMRZ30oTv1TRbflym9uCSJqrCwXYTMXC/Sage%20Holding%20out%20hand%20Purple%20heart.png",
"model": "dev",
"prompt": "sage, same face style and proportions as reference. Gentle natural smile showing a few upper teeth, purple hair, glasses, purple heart on shirt. \n--no extra hands, no distortion, no watermark, no misaligned eyes\n\n\n\n\n\n\n\n\n\n\n",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 3,
"output_quality": 80,
"prompt_strength": 0.4,
"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 2.47s Using seed: 16207 Prompt: sage, same face style and proportions as reference. Gentle natural smile showing a few upper teeth, purple hair, glasses, purple heart on shirt. --no extra hands, no distortion, no watermark, no misaligned eyes Input image size: 1024x1024 [!] Resizing input image from 1024x1024 to 1024x1024 [!] img2img mode 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:02, 4.77it/s] 17%|█▋ | 2/12 [00:00<00:02, 4.17it/s] 25%|██▌ | 3/12 [00:00<00:02, 4.01it/s] 33%|███▎ | 4/12 [00:00<00:02, 3.94it/s] 42%|████▏ | 5/12 [00:01<00:01, 3.90it/s] 50%|█████ | 6/12 [00:01<00:01, 3.87it/s] 58%|█████▊ | 7/12 [00:01<00:01, 3.86it/s] 67%|██████▋ | 8/12 [00:02<00:01, 3.84it/s] 75%|███████▌ | 9/12 [00:02<00:00, 3.84it/s] 83%|████████▎ | 10/12 [00:02<00:00, 3.83it/s] 92%|█████████▏| 11/12 [00:02<00:00, 3.83it/s] 100%|██████████| 12/12 [00:03<00:00, 3.83it/s] 100%|██████████| 12/12 [00:03<00:00, 3.89it/s] Total safe images: 1 out of 1
Version Details
- Version ID
f60300c53d7777182953042ca279eb7700b7d71818c3139f3af888fe660cf2c9- Version Created
- August 28, 2025