moicarmonas/3rdmoises_generator_oldversion 🖼️🔢❓📝✓ → 🖼️

▶️ 182 runs 📅 Jul 2025 ⚙️ Cog 0.15.3
image-to-image lora lora-person text-to-image

About

.

Example Output

Prompt:

"

A YouTube thumbnail featuring Moises, a fit and good-looking young Latino man in his early 20s with short dark curly hair, tan skin, and a confident look. He is standing in front of a blackboard-style comparison chart with two columns labeled “TRADING” and another (pixelated for now, could be labeled “ECOM” or “DIGITAL”).

Moises is wearing a clean white fitted t-shirt, standing with arms extended outward, palms slightly up, in a relaxed yet confident pose. His facial expression is calm but assertive, as if he’s clearly presenting the better choice.

The “TRADING” side has red X marks next to words like:

❌ FREEDOM

❌ PROFITS

❌ EASY

The other column (right side, green) has green checkmarks next to the same words:

✅ FREEDOM

✅ PROFITS

✅ EASY

The overall vibe is modern, smart, and persuasive, showing Moises as someone who confidently contrasts two business models and subtly guides the viewer toward the better path.

Let me know if you want a Spanish version or specific branding like "ECOM" or "AMAZON" added.

"

Output

Example outputExample outputExample outputExample output

Performance Metrics

22.62s Prediction Time
23.44s Total Time
All Input Parameters 
{
  "image": "https://img.youtube.com/vi/uCjcc1TXk5c/maxresdefault.jpg",
  "model": "dev",
  "prompt": "A YouTube thumbnail featuring Moises, a fit and good-looking young Latino man in his early 20s with short dark curly hair, tan skin, and a confident look. He is standing in front of a blackboard-style comparison chart with two columns labeled “TRADING” and another (pixelated for now, could be labeled “ECOM” or “DIGITAL”).\n\nMoises is wearing a clean white fitted t-shirt, standing with arms extended outward, palms slightly up, in a relaxed yet confident pose. His facial expression is calm but assertive, as if he’s clearly presenting the better choice.\n\nThe “TRADING” side has red X marks next to words like:\n\n❌ FREEDOM\n\n❌ PROFITS\n\n❌ EASY\n\nThe other column (right side, green) has green checkmarks next to the same words:\n\n✅ FREEDOM\n\n✅ PROFITS\n\n✅ EASY\n\nThe overall vibe is modern, smart, and persuasive, showing Moises as someone who confidently contrasts two business models and subtly guides the viewer toward the better path.\n\nLet me know if you want a Spanish version or specific branding like \"ECOM\" or \"AMAZON\" added.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "16:9",
  "output_format": "webp",
  "guidance_scale": 2.8,
  "output_quality": 80,
  "prompt_strength": 0.85,
  "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=25969028055040
Downloading weights
2025-07-30T17:11:28Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp5_rjw234/weights url=https://replicate.delivery/xezq/lpTkRorypbYwM1UGatnh5LVGc1SAIG0gc3zqJXIONROL9fiKA/trained_model.tar
2025-07-30T17:11:28Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-07-30T17:11:28Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/lpTkRorypbYwM1UGatnh5LVGc1SAIG0gc3zqJXIONROL9fiKA/trained_model.tar url=https://replicate.delivery/xezq/lpTkRorypbYwM1UGatnh5LVGc1SAIG0gc3zqJXIONROL9fiKA/trained_model.tar
2025-07-30T17:11:28Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/15ad93d323e3bc915edf1de1d166c78bd11edc87103b75b270c23f09eb8a36bb?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=20250730T171128Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=b7b403313e6bfe75ae50ad2b7e446eff7a1307e150465b57a0ee026ce0f3c692 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/lpTkRorypbYwM1UGatnh5LVGc1SAIG0gc3zqJXIONROL9fiKA/trained_model.tar
2025-07-30T17:11:29Z | INFO  | [ Complete ] dest=/tmp/tmp5_rjw234/weights size="172 MB" total_elapsed=0.402s url=https://replicate.delivery/xezq/lpTkRorypbYwM1UGatnh5LVGc1SAIG0gc3zqJXIONROL9fiKA/trained_model.tar
Downloaded weights in 0.46s
Loaded LoRAs in 1.04s
Using seed: 58322
Prompt: A YouTube thumbnail featuring Moises, a fit and good-looking young Latino man in his early 20s with short dark curly hair, tan skin, and a confident look. He is standing in front of a blackboard-style comparison chart with two columns labeled “TRADING” and another (pixelated for now, could be labeled “ECOM” or “DIGITAL”).
Moises is wearing a clean white fitted t-shirt, standing with arms extended outward, palms slightly up, in a relaxed yet confident pose. His facial expression is calm but assertive, as if he’s clearly presenting the better choice.
The “TRADING” side has red X marks next to words like:
❌ FREEDOM
❌ PROFITS
❌ EASY
The other column (right side, green) has green checkmarks next to the same words:
✅ FREEDOM
✅ PROFITS
✅ EASY
The overall vibe is modern, smart, and persuasive, showing Moises as someone who confidently contrasts two business models and subtly guides the viewer toward the better path.
Let me know if you want a Spanish version or specific branding like "ECOM" or "AMAZON" added.
Input image size: 1280x720
[!] Resizing input image from 1280x720 to 1280x720
[!] img2img mode
  0%|          | 0/24 [00:00<?, ?it/s]
  4%|▍         | 1/24 [00:00<00:15,  1.45it/s]
  8%|▊         | 2/24 [00:01<00:17,  1.26it/s]
 12%|█▎        | 3/24 [00:02<00:17,  1.21it/s]
 17%|█▋        | 4/24 [00:03<00:16,  1.19it/s]
 21%|██        | 5/24 [00:04<00:16,  1.18it/s]
 25%|██▌       | 6/24 [00:05<00:15,  1.17it/s]
 29%|██▉       | 7/24 [00:05<00:14,  1.17it/s]
 33%|███▎      | 8/24 [00:06<00:13,  1.17it/s]
 38%|███▊      | 9/24 [00:07<00:12,  1.16it/s]
 42%|████▏     | 10/24 [00:08<00:12,  1.16it/s]
 46%|████▌     | 11/24 [00:09<00:11,  1.16it/s]
 50%|█████     | 12/24 [00:10<00:10,  1.16it/s]
 54%|█████▍    | 13/24 [00:11<00:09,  1.16it/s]
 58%|█████▊    | 14/24 [00:11<00:08,  1.16it/s]
 62%|██████▎   | 15/24 [00:12<00:07,  1.16it/s]
 67%|██████▋   | 16/24 [00:13<00:06,  1.16it/s]
 71%|███████   | 17/24 [00:14<00:06,  1.16it/s]
 75%|███████▌  | 18/24 [00:15<00:05,  1.16it/s]
 79%|███████▉  | 19/24 [00:16<00:04,  1.16it/s]
 83%|████████▎ | 20/24 [00:17<00:03,  1.16it/s]
 88%|████████▊ | 21/24 [00:17<00:02,  1.16it/s]
 92%|█████████▏| 22/24 [00:18<00:01,  1.16it/s]
 96%|█████████▌| 23/24 [00:19<00:00,  1.16it/s]
100%|██████████| 24/24 [00:20<00:00,  1.16it/s]
100%|██████████| 24/24 [00:20<00:00,  1.17it/s]
Total safe images: 4 out of 4
Version Details
Version ID
214591a08f5e60ddfc97576ebe4562491b8d559920b0e17ae04caa1fc0291270
Version Created
July 30, 2025
Run on Replicate →