shannonlcraft/scraft1 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"
scraft1 is a thinner bald white man with beard and is seated in a well-lit, contemporary workspace that blends comfort with professionalism. He faces the camera directly, with a poised and composed demeanor. His expression is calm. His neatly groomed beard and clean-shaven scalp emphasize his polished appearance.
He is dressed in a fitted long sleeved black top, simple yet elegant, which contrasts sharply with the warm tones of the environment. Around his neck, a gold chain adds a touch of sophistication, catching the light subtly and drawing attention to his overall styling. wearing modern elegant black sunglasses
The camera captures scraft1 in a medium shot at eye level, with blue eyes, focusing on his upper body while leaning against the wall and allowing for a clear view of both his expression and the surrounding environment. The background features a dark black brick wall adorned with minimalistic decor, including small potted plants and wall-mounted lights that cast warm, soft glows. A set of furniture, including modern armchairs and tables, creates a cozy yet professional ambiance.
The lighting is warm and evenly diffused, blending natural daylight with artificial light sources. This balance enhances the texture of the wall and the metallic sheen of scraft1's chain, while subtly illuminating his facial features.
The mood of the image is thoughtful and inviting, striking a balance between professionalism and approachability. The minimalist design of the setting, paired with scraft1's calm demeanor and sleek outfit, creates a harmonious and engaging visual composition that conveys focus and modern sophistication.
"Output
Performance Metrics
27.94s
Prediction Time
28.11s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "scraft1 is a thinner bald white man with beard and is seated in a well-lit, contemporary workspace that blends comfort with professionalism. He faces the camera directly, with a poised and composed demeanor. His expression is calm. His neatly groomed beard and clean-shaven scalp emphasize his polished appearance.\n\nHe is dressed in a fitted long sleeved black top, simple yet elegant, which contrasts sharply with the warm tones of the environment. Around his neck, a gold chain adds a touch of sophistication, catching the light subtly and drawing attention to his overall styling. wearing modern elegant black sunglasses\n\nThe camera captures scraft1 in a medium shot at eye level, with blue eyes, focusing on his upper body while leaning against the wall and allowing for a clear view of both his expression and the surrounding environment. The background features a dark black brick wall adorned with minimalistic decor, including small potted plants and wall-mounted lights that cast warm, soft glows. A set of furniture, including modern armchairs and tables, creates a cozy yet professional ambiance.\n\nThe lighting is warm and evenly diffused, blending natural daylight with artificial light sources. This balance enhances the texture of the wall and the metallic sheen of scraft1's chain, while subtly illuminating his facial features.\n\nThe mood of the image is thoughtful and inviting, striking a balance between professionalism and approachability. The minimalist design of the setting, paired with scraft1's calm demeanor and sleek outfit, creates a harmonious and engaging visual composition that conveys focus and modern sophistication.",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 4,
"aspect_ratio": "16:9",
"output_format": "png",
"guidance_scale": 3,
"output_quality": 90,
"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
2025-01-14 17:34:59.285 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2025-01-14 17:34:59.286 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 93%|█████████▎| 284/304 [00:00<00:00, 2830.76it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2674.32it/s] 2025-01-14 17:34:59.400 | SUCCESS | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.11s free=29405053743104 Downloading weights 2025-01-14T17:34:59Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp20v_1gm9/weights url=https://replicate.delivery/xezq/e0lwQaTI1er5I0SsY3BISmxuFzMEYekSfsqeSlCoUCZTlcngC/trained_model.tar 2025-01-14T17:35:01Z | INFO | [ Complete ] dest=/tmp/tmp20v_1gm9/weights size="172 MB" total_elapsed=2.519s url=https://replicate.delivery/xezq/e0lwQaTI1er5I0SsY3BISmxuFzMEYekSfsqeSlCoUCZTlcngC/trained_model.tar Downloaded weights in 2.55s 2025-01-14 17:35:01.946 | INFO | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/e435174482ded1ec 2025-01-14 17:35:02.015 | INFO | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded 2025-01-14 17:35:02.015 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2025-01-14 17:35:02.015 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 93%|█████████▎| 284/304 [00:00<00:00, 2834.04it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2677.96it/s] 2025-01-14 17:35:02.129 | SUCCESS | fp8.lora_loading:load_lora:539 - LoRA applied in 0.18s Using seed: 46277 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, 5.00it/s] 6it [00:01, 4.90it/s] 7it [00:01, 4.88it/s] 8it [00:01, 4.87it/s] 9it [00:01, 4.86it/s] 10it [00:01, 4.84it/s] 11it [00:02, 4.83it/s] 12it [00:02, 4.83it/s] 13it [00:02, 4.83it/s] 14it [00:02, 4.83it/s] 15it [00:03, 4.82it/s] 16it [00:03, 4.81it/s] 17it [00:03, 4.81it/s] 18it [00:03, 4.83it/s] 19it [00:03, 4.82it/s] 20it [00:04, 4.82it/s] 21it [00:04, 4.81it/s] 22it [00:04, 4.82it/s] 23it [00:04, 4.82it/s] 24it [00:04, 4.81it/s] 25it [00:05, 4.81it/s] 26it [00:05, 4.80it/s] 27it [00:05, 4.81it/s] 28it [00:05, 4.81it/s] 28it [00:05, 4.89it/s] 0it [00:00, ?it/s] 1it [00:00, 4.83it/s] 2it [00:00, 4.82it/s] 3it [00:00, 4.81it/s] 4it [00:00, 4.82it/s] 5it [00:01, 4.81it/s] 6it [00:01, 4.80it/s] 7it [00:01, 4.80it/s] 8it [00:01, 4.79it/s] 9it [00:01, 4.80it/s] 10it [00:02, 4.80it/s] 11it [00:02, 4.80it/s] 12it [00:02, 4.80it/s] 13it [00:02, 4.79it/s] 14it [00:02, 4.80it/s] 15it [00:03, 4.81it/s] 16it [00:03, 4.81it/s] 17it [00:03, 4.81it/s] 18it [00:03, 4.80it/s] 19it [00:03, 4.81it/s] 20it [00:04, 4.81it/s] 21it [00:04, 4.82it/s] 22it [00:04, 4.82it/s] 23it [00:04, 4.81it/s] 24it [00:04, 4.80it/s] 25it [00:05, 4.80it/s] 26it [00:05, 4.82it/s] 27it [00:05, 4.81it/s] 28it [00:05, 4.81it/s] 28it [00:05, 4.81it/s] 0it [00:00, ?it/s] 1it [00:00, 4.83it/s] 2it [00:00, 4.81it/s] 3it [00:00, 4.83it/s] 4it [00:00, 4.82it/s] 5it [00:01, 4.83it/s] 6it [00:01, 4.82it/s] 7it [00:01, 4.81it/s] 8it [00:01, 4.80it/s] 9it [00:01, 4.80it/s] 10it [00:02, 4.80it/s] 11it [00:02, 4.80it/s] 12it [00:02, 4.80it/s] 13it [00:02, 4.81it/s] 14it [00:02, 4.81it/s] 15it [00:03, 4.80it/s] 16it [00:03, 4.81it/s] 17it [00:03, 4.80it/s] 18it [00:03, 4.80it/s] 19it [00:03, 4.81it/s] 20it [00:04, 4.81it/s] 21it [00:04, 4.81it/s] 22it [00:04, 4.81it/s] 23it [00:04, 4.80it/s] 24it [00:04, 4.80it/s] 25it [00:05, 4.80it/s] 26it [00:05, 4.80it/s] 27it [00:05, 4.80it/s] 28it [00:05, 4.80it/s] 28it [00:05, 4.80it/s] 0it [00:00, ?it/s] 1it [00:00, 4.83it/s] 2it [00:00, 4.82it/s] 3it [00:00, 4.81it/s] 4it [00:00, 4.77it/s] 5it [00:01, 4.78it/s] 6it [00:01, 4.79it/s] 7it [00:01, 4.79it/s] 8it [00:01, 4.79it/s] 9it [00:01, 4.78it/s] 10it [00:02, 4.79it/s] 11it [00:02, 4.80it/s] 12it [00:02, 4.80it/s] 13it [00:02, 4.78it/s] 14it [00:02, 4.79it/s] 15it [00:03, 4.79it/s] 16it [00:03, 4.80it/s] 17it [00:03, 4.80it/s] 18it [00:03, 4.80it/s] 19it [00:03, 4.80it/s] 20it [00:04, 4.80it/s] 21it [00:04, 4.80it/s] 22it [00:04, 4.81it/s] 23it [00:04, 4.81it/s] 24it [00:05, 4.80it/s] 25it [00:05, 4.81it/s] 26it [00:05, 4.81it/s] 27it [00:05, 4.80it/s] 28it [00:05, 4.81it/s] 28it [00:05, 4.80it/s] Total safe images: 4 out of 4
Version Details
- Version ID
fb2535977e6414378c38030e4a99401a2092967060c00542258f88fcd409656c- Version Created
- January 14, 2025