abubakar0111/zek 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"
“Create a sharp, highly detailed realistic image of a man with a long bro flow haircut and a short beard, dressed in a well-tailored white suit, standing confidently at a podium or on stage at a tech event. He is holding a microphone in one hand, with his other hand raised, explaining a concept with clarity and authority. His expression is serious yet approachable, exuding confidence and expertise. His face is clean with smooth skin and light pink lips, adding a soft, natural touch to his appearance. The long bro flow haircut features hair that cascades naturally to his shoulders, styled with a relaxed yet professional flow that complements his polished look.
The setting is a modern, sleek tech event with clean, minimalistic design elements. Professional lighting highlights his face, casting a soft glow and emphasizing his features with a light, almost ethereal quality. The camera angle is perfectly aligned to capture him from a slightly low perspective, giving him a commanding presence. The background is blurred with soft, indistinct silhouettes of the audience, ensuring the focus remains on him. The atmosphere is sophisticated and high-tech, with the image crisp, detailed, and sharp, with perfect lighting and shadow play to enhance the professional and modern mood.”
"Output
Performance Metrics
7.89s
Prediction Time
8.04s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "“Create a sharp, highly detailed realistic image of a man with a long bro flow haircut and a short beard, dressed in a well-tailored white suit, standing confidently at a podium or on stage at a tech event. He is holding a microphone in one hand, with his other hand raised, explaining a concept with clarity and authority. His expression is serious yet approachable, exuding confidence and expertise. His face is clean with smooth skin and light pink lips, adding a soft, natural touch to his appearance. The long bro flow haircut features hair that cascades naturally to his shoulders, styled with a relaxed yet professional flow that complements his polished look.\n\nThe setting is a modern, sleek tech event with clean, minimalistic design elements. Professional lighting highlights his face, casting a soft glow and emphasizing his features with a light, almost ethereal quality. The camera angle is perfectly aligned to capture him from a slightly low perspective, giving him a commanding presence. The background is blurred with soft, indistinct silhouettes of the audience, ensuring the focus remains on him. The atmosphere is sophisticated and high-tech, with the image crisp, detailed, and sharp, with perfect lighting and shadow play to enhance the professional and modern mood.”",
"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": 0.8,
"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
2024-12-29 14:55:24.134 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2024-12-29 14:55:24.134 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 93%|█████████▎| 283/304 [00:00<00:00, 2809.13it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2653.16it/s] 2024-12-29 14:55:24.249 | SUCCESS | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s free=30049941446656 Downloading weights 2024-12-29T14:55:24Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpslj1jegl/weights url=https://replicate.delivery/xezq/KAbSsogfpTyDN6LIbQIrezySYeqR60ZFdeeRVCLMcjezPBJeJA/trained_model.tar 2024-12-29T14:55:25Z | INFO | [ Complete ] dest=/tmp/tmpslj1jegl/weights size="172 MB" total_elapsed=1.404s url=https://replicate.delivery/xezq/KAbSsogfpTyDN6LIbQIrezySYeqR60ZFdeeRVCLMcjezPBJeJA/trained_model.tar Downloaded weights in 1.43s 2024-12-29 14:55:25.680 | INFO | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/b7adcce7585f5763 2024-12-29 14:55:25.750 | INFO | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded 2024-12-29 14:55:25.750 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2024-12-29 14:55:25.751 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 93%|█████████▎| 283/304 [00:00<00:00, 2813.83it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2657.62it/s] 2024-12-29 14:55:25.865 | SUCCESS | fp8.lora_loading:load_lora:539 - LoRA applied in 0.19s Using seed: 42623 0it [00:00, ?it/s] 1it [00:00, 8.34it/s] 2it [00:00, 5.83it/s] 3it [00:00, 5.30it/s] 4it [00:00, 5.08it/s] 5it [00:00, 4.93it/s] 6it [00:01, 4.86it/s] 7it [00:01, 4.83it/s] 8it [00:01, 4.82it/s] 9it [00:01, 4.80it/s] 10it [00:02, 4.77it/s] 11it [00:02, 4.76it/s] 12it [00:02, 4.77it/s] 13it [00:02, 4.77it/s] 14it [00:02, 4.77it/s] 15it [00:03, 4.76it/s] 16it [00:03, 4.75it/s] 17it [00:03, 4.75it/s] 18it [00:03, 4.76it/s] 19it [00:03, 4.76it/s] 20it [00:04, 4.75it/s] 21it [00:04, 4.75it/s] 22it [00:04, 4.75it/s] 23it [00:04, 4.75it/s] 24it [00:04, 4.74it/s] 25it [00:05, 4.74it/s] 26it [00:05, 4.75it/s] 27it [00:05, 4.75it/s] 28it [00:05, 4.75it/s] 28it [00:05, 4.83it/s] Total safe images: 1 out of 1
Version Details
- Version ID
6e1280bb86b48afece0d8914516e82be8dadfac1cb4a520f23f12d34e8d9ad47- Version Created
- December 7, 2024