moicarmonas/2ndmoises_generator šŸ–¼ļøšŸ”¢ā“šŸ“āœ“ → šŸ–¼ļø

ā–¶ļø 18 runs šŸ“… Jul 2025 āš™ļø Cog 0.13.6
image-to-image lora lora-person text-to-image

About

Example Output

Prompt:

"

A realistic YouTube thumbnail featuring Moises, a young Latino man in his early 20s, with short curly dark hair, tan skin, and a light stubble. He is seated at a wooden desk in a cozy, well-lit room, wearing a light gray t-shirt, over-ear white headphones, and a smartwatch on his left wrist.

Moises is focused and writing in a notebook, with a tablet on a keyboard stand to his left showing an open YouTube video or document. His posture is slightly leaned forward, showing deep concentration.

To the top left of the image, include a large white rounded box with the PayPal logo and the text:
ā€œ+$10,780ā€ in bold, bright green, centered inside the box to indicate income.

The vibe is productive and aspirational, portraying Moises as someone making real money online from home.

"

Output

Example outputExample outputExample outputExample output

Performance Metrics

21.64s Prediction Time
21.65s Total Time
All Input Parameters
{
  "image": "https://img.youtube.com/vi/wD9hMYbijDA/maxresdefault.jpg",
  "model": "dev",
  "prompt": "A realistic YouTube thumbnail featuring Moises, a young Latino man in his early 20s, with short curly dark hair, tan skin, and a light stubble. He is seated at a wooden desk in a cozy, well-lit room, wearing a light gray t-shirt, over-ear white headphones, and a smartwatch on his left wrist.\n\nMoises is focused and writing in a notebook, with a tablet on a keyboard stand to his left showing an open YouTube video or document. His posture is slightly leaned forward, showing deep concentration.\n\nTo the top left of the image, include a large white rounded box with the PayPal logo and the text:\nā€œ+$10,780ā€ in bold, bright green, centered inside the box to indicate income.\n\nThe vibe is productive and aspirational, portraying Moises as someone making real money online from home.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "16:9",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}
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 • Items Type: string • Items Format: uri

Example Execution Logs
free=25802448027648
Downloading weights
2025-07-30T16:36:09Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpg2a_3fg_/weights url=https://replicate.delivery/xezq/WSxNNLF58NYAOFm0vyX0LLhnXm2NvrCvca0oPDMxe5vHqfFVA/flux-lora.tar
2025-07-30T16:36:09Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-07-30T16:36:09Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/WSxNNLF58NYAOFm0vyX0LLhnXm2NvrCvca0oPDMxe5vHqfFVA/flux-lora.tar url=https://replicate.delivery/xezq/WSxNNLF58NYAOFm0vyX0LLhnXm2NvrCvca0oPDMxe5vHqfFVA/flux-lora.tar
2025-07-30T16:36:09Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/3982af73473c8598e22c4b7484fec878362c5fa8ff0824f17b83ca0ef975eff3?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250730%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250730T163609Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=5a3791f12570017d74e1c05d809c7f0b044779c5025605217ad00e9b83c3dc11 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/WSxNNLF58NYAOFm0vyX0LLhnXm2NvrCvca0oPDMxe5vHqfFVA/flux-lora.tar
2025-07-30T16:36:09Z | INFO  | [ Complete ] dest=/tmp/tmpg2a_3fg_/weights size="172 MB" total_elapsed=0.244s url=https://replicate.delivery/xezq/WSxNNLF58NYAOFm0vyX0LLhnXm2NvrCvca0oPDMxe5vHqfFVA/flux-lora.tar
Downloaded weights in 0.31s
Loaded LoRAs in 0.84s
Using seed: 41568
Prompt: A realistic YouTube thumbnail featuring Moises, a young Latino man in his early 20s, with short curly dark hair, tan skin, and a light stubble. He is seated at a wooden desk in a cozy, well-lit room, wearing a light gray t-shirt, over-ear white headphones, and a smartwatch on his left wrist.
Moises is focused and writing in a notebook, with a tablet on a keyboard stand to his left showing an open YouTube video or document. His posture is slightly leaned forward, showing deep concentration.
To the top left of the image, include a large white rounded box with the PayPal logo and the text:
ā€œ+$10,780ā€ in bold, bright green, centered inside the box to indicate income.
The vibe is productive and aspirational, portraying Moises as someone making real money online from home.
Input image size: 1280x720
[!] Resizing input image from 1280x720 to 1280x720
[!] img2img mode
  0%|          | 0/23 [00:00<?, ?it/s]
  4%|ā–         | 1/23 [00:00<00:14,  1.47it/s]
  9%|ā–Š         | 2/23 [00:01<00:16,  1.27it/s]
 13%|ā–ˆā–Ž        | 3/23 [00:02<00:16,  1.22it/s]
 17%|ā–ˆā–‹        | 4/23 [00:03<00:15,  1.19it/s]
 22%|ā–ˆā–ˆā–       | 5/23 [00:04<00:15,  1.18it/s]
 26%|ā–ˆā–ˆā–Œ       | 6/23 [00:04<00:14,  1.18it/s]
 30%|ā–ˆā–ˆā–ˆ       | 7/23 [00:05<00:13,  1.17it/s]
 35%|ā–ˆā–ˆā–ˆā–      | 8/23 [00:06<00:12,  1.17it/s]
 39%|ā–ˆā–ˆā–ˆā–‰      | 9/23 [00:07<00:12,  1.16it/s]
 43%|ā–ˆā–ˆā–ˆā–ˆā–Ž     | 10/23 [00:08<00:11,  1.16it/s]
 48%|ā–ˆā–ˆā–ˆā–ˆā–Š     | 11/23 [00:09<00:10,  1.16it/s]
 52%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–    | 12/23 [00:10<00:09,  1.16it/s]
 57%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–‹    | 13/23 [00:11<00:08,  1.16it/s]
 61%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆ    | 14/23 [00:11<00:07,  1.16it/s]
 65%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–Œ   | 15/23 [00:12<00:06,  1.16it/s]
 70%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–‰   | 16/23 [00:13<00:06,  1.16it/s]
 74%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–  | 17/23 [00:14<00:05,  1.16it/s]
 78%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–Š  | 18/23 [00:15<00:04,  1.16it/s]
 83%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–Ž | 19/23 [00:16<00:03,  1.16it/s]
 87%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–‹ | 20/23 [00:17<00:02,  1.16it/s]
 91%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–| 21/23 [00:17<00:01,  1.16it/s]
 96%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–Œ| 22/23 [00:18<00:00,  1.16it/s]
100%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆ| 23/23 [00:19<00:00,  1.16it/s]
100%|ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆ| 23/23 [00:19<00:00,  1.17it/s]
Total safe images: 4 out of 4
Version Details
Version ID
7ae928ae3e6f1614129b139f34503ff4e91e922e7487658a47ad600bca16d5b0
Version Created
July 30, 2025
Run on Replicate →