10thecreator/ai_moment_version_3 πŸ–ΌοΈπŸ”’β“πŸ“βœ“ β†’ πŸ–ΌοΈ

▢️ 69 runs πŸ“… Mar 2025 βš™οΈ Cog 0.13.7
image-inpainting image-to-image lora product-photography text-to-image

About

Example Output

Prompt:

"A sleek, high-end advertising photo of momv, featuring a beautifully chilled can with fresh condensation, placed against a dreamy, sunlit backdrop. The lighting is soft and natural, with golden-hour hues illuminating the can, making it look irresistibly refreshing. A crystal-clear glass filled with the lightly effervescent beverage sits beside it, with subtle reflections enhancing its purity. The background blends calm tones of lavender, warm peach, and deep sunset orange, mirroring momv vibrant, wellness-driven aesthetic. The scene feels like a moment of serenityβ€”perfect for a health-conscious, modern audience seeking balance and relaxation. The composition is clean, aspirational, and editorial-worthy, making it ideal for high-end print and digital ad campaigns. Please make sure the spelling of "moment" "0 sugar added" "still adaptoghens & botanical drink" "drink your meditation" are on the can accordingly in the right spots on momv"

Output

Example outputExample outputExample outputExample output

Performance Metrics

56.20s Prediction Time
61.52s Total Time
All Input Parameters
{
  "model": "dev",
  "prompt": "A sleek, high-end advertising photo of momv, featuring a beautifully chilled can with fresh condensation, placed against a dreamy, sunlit backdrop. The lighting is soft and natural, with golden-hour hues illuminating the can, making it look irresistibly refreshing. A crystal-clear glass filled with the lightly effervescent beverage sits beside it, with subtle reflections enhancing its purity.  The background blends calm tones of lavender, warm peach, and deep sunset orange, mirroring momv vibrant, wellness-driven aesthetic. The scene feels like a moment of serenityβ€”perfect for a health-conscious, modern audience seeking balance and relaxation. The composition is clean, aspirational, and editorial-worthy, making it ideal for high-end print and digital ad campaigns. Please make sure  the spelling of  \"moment\" \"0 sugar added\" \"still adaptoghens & botanical drink\"  \"drink your meditation\" are on the can accordingly in the right spots on momv",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "4:5",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 50
}
Input Parameters
mask Type: string
Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
seed Type: integer
Random seed. Set for reproducible generation
image Type: string
Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
model Default: dev
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 Type: integerRange: 256 - 1440
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 Type: integerRange: 256 - 1440
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) Type: string
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 Type: booleanDefault: false
Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
extra_lora Type: string
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 Type: numberDefault: 1Range: -1 - 3
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 Default: 1
Approximate number of megapixels for generated image
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of outputs to generate
aspect_ratio Default: 1:1
Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
output_format Default: webp
Format of the output images
guidance_scale Type: numberDefault: 3Range: 0 - 10
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 Type: integerDefault: 80Range: 0 - 100
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 Type: numberDefault: 0.8Range: 0 - 1
Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
extra_lora_scale Type: numberDefault: 1Range: -1 - 3
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 Type: string
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 Type: integerDefault: 28Range: 1 - 50
Number of denoising steps. More steps can give more detailed images, but take longer.
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images.
Output Schema

Output

Type: array β€’ Items Type: string β€’ Items Format: uri

Example Execution Logs
free=28849194762240
Downloading weights
2025-03-08T15:29:04Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpnm3tu_yg/weights url=https://replicate.delivery/xezq/wTenIrnEEP12YSMI5GTfgGryZHOpdULrQFyhuJbaGzFfECtoA/trained_model.tar
2025-03-08T15:29:11Z | INFO  | [ Complete ] dest=/tmp/tmpnm3tu_yg/weights size="344 MB" total_elapsed=7.744s url=https://replicate.delivery/xezq/wTenIrnEEP12YSMI5GTfgGryZHOpdULrQFyhuJbaGzFfECtoA/trained_model.tar
Downloaded weights in 7.78s
Loaded LoRAs in 8.37s
Using seed: 11594
Prompt: A sleek, high-end advertising photo of momv, featuring a beautifully chilled can with fresh condensation, placed against a dreamy, sunlit backdrop. The lighting is soft and natural, with golden-hour hues illuminating the can, making it look irresistibly refreshing. A crystal-clear glass filled with the lightly effervescent beverage sits beside it, with subtle reflections enhancing its purity.  The background blends calm tones of lavender, warm peach, and deep sunset orange, mirroring momv vibrant, wellness-driven aesthetic. The scene feels like a moment of serenityβ€”perfect for a health-conscious, modern audience seeking balance and relaxation. The composition is clean, aspirational, and editorial-worthy, making it ideal for high-end print and digital ad campaigns. Please make sure  the spelling of  "moment" "0 sugar added" "still adaptoghens & botanical drink"  "drink your meditation" are on the can accordingly in the right spots on momv
[!] txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:01<01:12,  1.48s/it]
  4%|▍         | 2/50 [00:02<00:49,  1.03s/it]
  6%|β–Œ         | 3/50 [00:03<00:44,  1.05it/s]
  8%|β–Š         | 4/50 [00:03<00:42,  1.09it/s]
 10%|β–ˆ         | 5/50 [00:04<00:40,  1.11it/s]
 12%|β–ˆβ–        | 6/50 [00:05<00:39,  1.12it/s]
 14%|β–ˆβ–        | 7/50 [00:06<00:37,  1.13it/s]
 16%|β–ˆβ–Œ        | 8/50 [00:07<00:37,  1.13it/s]
 18%|β–ˆβ–Š        | 9/50 [00:08<00:35,  1.14it/s]
 20%|β–ˆβ–ˆ        | 10/50 [00:09<00:35,  1.14it/s]
 22%|β–ˆβ–ˆβ–       | 11/50 [00:10<00:34,  1.14it/s]
 24%|β–ˆβ–ˆβ–       | 12/50 [00:10<00:33,  1.14it/s]
 26%|β–ˆβ–ˆβ–Œ       | 13/50 [00:11<00:32,  1.15it/s]
 28%|β–ˆβ–ˆβ–Š       | 14/50 [00:12<00:31,  1.15it/s]
 30%|β–ˆβ–ˆβ–ˆ       | 15/50 [00:13<00:30,  1.15it/s]
 32%|β–ˆβ–ˆβ–ˆβ–      | 16/50 [00:14<00:29,  1.14it/s]
 34%|β–ˆβ–ˆβ–ˆβ–      | 17/50 [00:15<00:28,  1.15it/s]
 36%|β–ˆβ–ˆβ–ˆβ–Œ      | 18/50 [00:16<00:27,  1.15it/s]
 38%|β–ˆβ–ˆβ–ˆβ–Š      | 19/50 [00:16<00:27,  1.15it/s]
 40%|β–ˆβ–ˆβ–ˆβ–ˆ      | 20/50 [00:17<00:26,  1.15it/s]
 42%|β–ˆβ–ˆβ–ˆβ–ˆβ–     | 21/50 [00:18<00:25,  1.15it/s]
 44%|β–ˆβ–ˆβ–ˆβ–ˆβ–     | 22/50 [00:19<00:24,  1.15it/s]
 46%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ     | 23/50 [00:20<00:23,  1.15it/s]
 48%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š     | 24/50 [00:21<00:22,  1.15it/s]
 50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 25/50 [00:22<00:21,  1.15it/s]
 52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–    | 26/50 [00:23<00:20,  1.15it/s]
 54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–    | 27/50 [00:23<00:20,  1.15it/s]
 56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ    | 28/50 [00:24<00:19,  1.15it/s]
 58%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š    | 29/50 [00:25<00:18,  1.15it/s]
 60%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ    | 30/50 [00:26<00:17,  1.15it/s]
 62%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–   | 31/50 [00:27<00:16,  1.15it/s]
 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–   | 32/50 [00:28<00:15,  1.15it/s]
 66%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ   | 33/50 [00:29<00:14,  1.15it/s]
 68%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š   | 34/50 [00:30<00:13,  1.15it/s]
 70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ   | 35/50 [00:30<00:13,  1.15it/s]
 72%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–  | 36/50 [00:31<00:12,  1.15it/s]
 74%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–  | 37/50 [00:32<00:11,  1.15it/s]
 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 38/50 [00:33<00:10,  1.15it/s]
 78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š  | 39/50 [00:34<00:09,  1.15it/s]
 80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ  | 40/50 [00:35<00:08,  1.15it/s]
 82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 41/50 [00:36<00:07,  1.15it/s]
 84%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 42/50 [00:36<00:06,  1.15it/s]
 86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 43/50 [00:37<00:06,  1.15it/s]
 88%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 44/50 [00:38<00:05,  1.15it/s]
 90%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 45/50 [00:39<00:04,  1.15it/s]
 92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 46/50 [00:40<00:03,  1.15it/s]
 94%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 47/50 [00:41<00:02,  1.15it/s]
 96%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 48/50 [00:42<00:01,  1.15it/s]
 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 49/50 [00:43<00:00,  1.15it/s]
100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 50/50 [00:43<00:00,  1.15it/s]
100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 50/50 [00:43<00:00,  1.14it/s]
Total safe images: 4 out of 4
Version Details
Version ID
3d36f8f83b7289dcef67cbd892755ffb34bb54c054ea246c74484e67ab9b24db
Version Created
March 8, 2025
Run on Replicate β†’