viktorkonfyans/positivo-man 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"A modern, minimalistic office environment featuring an steel PM bootle on a polished wooden desk. In the background, a blurred figure is seen typing on a laptop, dressed in a smart-casual outfit, suggesting a professional yet approachable look. The office decor is sleek and contemporary, with a few green plants adding a touch of nature to the otherwise streamlined setting. The image conveys a sense of productivity and efficiency, positioning the bottle as an ideal hydration solution for busy professional man who value both aesthetics and functionality in their everyday items."
Output
Performance Metrics
21.29s
Prediction Time
30.29s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "A modern, minimalistic office environment featuring an steel PM bootle on a polished wooden desk. In the background, a blurred figure is seen typing on a laptop, dressed in a smart-casual outfit, suggesting a professional yet approachable look. The office decor is sleek and contemporary, with a few green plants adding a touch of nature to the otherwise streamlined setting. The image conveys a sense of productivity and efficiency, positioning the bottle as an ideal hydration solution for busy professional man who value both aesthetics and functionality in their everyday items.",
"lora_scale": 1,
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 3.5,
"output_quality": 90,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 40
}
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
Using seed: 56685 Prompt: A modern, minimalistic office environment featuring an steel PM bootle on a polished wooden desk. In the background, a blurred figure is seen typing on a laptop, dressed in a smart-casual outfit, suggesting a professional yet approachable look. The office decor is sleek and contemporary, with a few green plants adding a touch of nature to the otherwise streamlined setting. The image conveys a sense of productivity and efficiency, positioning the bottle as an ideal hydration solution for busy professional man who value both aesthetics and functionality in their everyday items. [!] txt2img mode Using dev model free=7457557479424 Downloading weights 2024-09-16T12:45:56Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp9p4qknii/weights url=https://replicate.delivery/yhqm/xn3vHP3OrHqPA1nOQ7fDG4luehIpLCfqT6baVxSfi5073q1NB/trained_model.tar 2024-09-16T12:45:57Z | INFO | [ Complete ] dest=/tmp/tmp9p4qknii/weights size="172 MB" total_elapsed=1.416s url=https://replicate.delivery/yhqm/xn3vHP3OrHqPA1nOQ7fDG4luehIpLCfqT6baVxSfi5073q1NB/trained_model.tar Downloaded weights in 1.44s Loaded LoRAs in 9.68s 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:11, 3.53it/s] 5%|▌ | 2/40 [00:00<00:09, 4.00it/s] 8%|▊ | 3/40 [00:00<00:09, 3.77it/s] 10%|█ | 4/40 [00:01<00:09, 3.68it/s] 12%|█▎ | 5/40 [00:01<00:09, 3.62it/s] 15%|█▌ | 6/40 [00:01<00:09, 3.59it/s] 18%|█▊ | 7/40 [00:01<00:09, 3.57it/s] 20%|██ | 8/40 [00:02<00:08, 3.56it/s] 22%|██▎ | 9/40 [00:02<00:08, 3.55it/s] 25%|██▌ | 10/40 [00:02<00:08, 3.54it/s] 28%|██▊ | 11/40 [00:03<00:08, 3.54it/s] 30%|███ | 12/40 [00:03<00:07, 3.54it/s] 32%|███▎ | 13/40 [00:03<00:07, 3.54it/s] 35%|███▌ | 14/40 [00:03<00:07, 3.54it/s] 38%|███▊ | 15/40 [00:04<00:07, 3.54it/s] 40%|████ | 16/40 [00:04<00:06, 3.53it/s] 42%|████▎ | 17/40 [00:04<00:06, 3.53it/s] 45%|████▌ | 18/40 [00:05<00:06, 3.53it/s] 48%|████▊ | 19/40 [00:05<00:05, 3.53it/s] 50%|█████ | 20/40 [00:05<00:05, 3.53it/s] 52%|█████▎ | 21/40 [00:05<00:05, 3.53it/s] 55%|█████▌ | 22/40 [00:06<00:05, 3.53it/s] 57%|█████▊ | 23/40 [00:06<00:04, 3.53it/s] 60%|██████ | 24/40 [00:06<00:04, 3.53it/s] 62%|██████▎ | 25/40 [00:07<00:04, 3.53it/s] 65%|██████▌ | 26/40 [00:07<00:03, 3.53it/s] 68%|██████▊ | 27/40 [00:07<00:03, 3.53it/s] 70%|███████ | 28/40 [00:07<00:03, 3.53it/s] 72%|███████▎ | 29/40 [00:08<00:03, 3.53it/s] 75%|███████▌ | 30/40 [00:08<00:02, 3.53it/s] 78%|███████▊ | 31/40 [00:08<00:02, 3.53it/s] 80%|████████ | 32/40 [00:09<00:02, 3.53it/s] 82%|████████▎ | 33/40 [00:09<00:01, 3.52it/s] 85%|████████▌ | 34/40 [00:09<00:01, 3.53it/s] 88%|████████▊ | 35/40 [00:09<00:01, 3.53it/s] 90%|█████████ | 36/40 [00:10<00:01, 3.53it/s] 92%|█████████▎| 37/40 [00:10<00:00, 3.53it/s] 95%|█████████▌| 38/40 [00:10<00:00, 3.53it/s] 98%|█████████▊| 39/40 [00:10<00:00, 3.53it/s] 100%|██████████| 40/40 [00:11<00:00, 3.53it/s] 100%|██████████| 40/40 [00:11<00:00, 3.55it/s]
Version Details
- Version ID
1842c73dd7655bd8b3de24946fb7a30932be42b921052e8bfa2fec363dc0364c- Version Created
- September 16, 2024