biggpt1/cart-boy 🖼️🔢❓📝✓ → 🖼️

▶️ 109 runs 📅 Jul 2025 ⚙️ Cog 0.13.6
cartoon cartoon-style image-to-image lora lora-person text-to-image

About

Example Output

Prompt:

"

Professional photoshoot of a TOK subject in cartoonish, cinematic cartoon style, set during a daring leap over a wild mountain river. Captured from a bold, cinematic angle: the camera is positioned low and close to the water, slightly behind and beneath the subject, on a dynamic diagonal that accentuates movement and scale. The perspective creates a sense of vertigo and immersion, as if the viewer is following the jump in real time. Wide shot.

The TOK subject, dressed in vivid traditional Ossetian attire—a striking red chokha (cherkeska) with decorative cartridges, crisp white shirt, black belt, and tall black boots—is caught mid-leap between mossy, towering boulders. Arms are flung wide for balance, body taut and athletic, the flowing fabric and sash trailing dramatically. His focus is intense, eyes locked forward on the landing rock, brows furrowed in determination and thrill.

Turbulent, foaming mountain water rushes beneath him, sparkling in the dawn light. The far bank is dotted with lush moss, delicate wildflowers, and weathered rocks. In the background, misty forested slopes and sweeping ridges frame the scene under a vivid morning sky.

The style is bold and cinematic: dramatic perspective, exaggerated sense of motion, dynamic lighting with streaks of sunlight cutting through cool mist, and painterly cartoon shading that enhances the epic, animated atmosphere.

Shot on a Canon R5 with a 24mm ultra-wide lens, using dramatic natural light and motion blur to amplify movement and immersion, perfect for a professional animated storyboard look.

"

Output

Example outputExample outputExample outputExample output

Performance Metrics

36.35s Prediction Time
36.43s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "Professional photoshoot of a TOK subject in cartoonish, cinematic cartoon style, set during a daring leap over a wild mountain river. Captured from a bold, cinematic angle: the camera is positioned low and close to the water, slightly behind and beneath the subject, on a dynamic diagonal that accentuates movement and scale. The perspective creates a sense of vertigo and immersion, as if the viewer is following the jump in real time. Wide shot.\n\nThe TOK subject, dressed in vivid traditional Ossetian attire—a striking red chokha (cherkeska) with decorative cartridges, crisp white shirt, black belt, and tall black boots—is caught mid-leap between mossy, towering boulders. Arms are flung wide for balance, body taut and athletic, the flowing fabric and sash trailing dramatically. His focus is intense, eyes locked forward on the landing rock, brows furrowed in determination and thrill.\n\nTurbulent, foaming mountain water rushes beneath him, sparkling in the dawn light. The far bank is dotted with lush moss, delicate wildflowers, and weathered rocks. In the background, misty forested slopes and sweeping ridges frame the scene under a vivid morning sky.\n\nThe style is bold and cinematic: dramatic perspective, exaggerated sense of motion, dynamic lighting with streaks of sunlight cutting through cool mist, and painterly cartoon shading that enhances the epic, animated atmosphere.\n\nShot on a Canon R5 with a 24mm ultra-wide lens, using dramatic natural light and motion blur to amplify movement and immersion, perfect for a professional animated storyboard look.\n\n",
  "go_fast": false,
  "extra_lora": "biggpt1/os-costume-male",
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "16:9",
  "output_format": "png",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 0.71,
  "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=24187415080960
Downloading weights
2025-07-20T12:58:07Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpspxw21ja/weights url=https://replicate.delivery/xezq/87BPGvMSmNIbHZdofe7mNpMHqh1I90yOm5mhEXhfZkpLsSFqA/flux-lora.tar
2025-07-20T12:58:07Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-07-20T12:58:07Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/87BPGvMSmNIbHZdofe7mNpMHqh1I90yOm5mhEXhfZkpLsSFqA/flux-lora.tar url=https://replicate.delivery/xezq/87BPGvMSmNIbHZdofe7mNpMHqh1I90yOm5mhEXhfZkpLsSFqA/flux-lora.tar
2025-07-20T12:58:07Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/72bac0bd15ebd2bd7dbb517fccc12bfbcc4fe61adc3e7147d2a202d33c854fa2?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250720%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250720T125807Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=351c56659ee30c73b4f2a084d654361fb13bac560d3050e86318851ac245f48d url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/87BPGvMSmNIbHZdofe7mNpMHqh1I90yOm5mhEXhfZkpLsSFqA/flux-lora.tar
2025-07-20T12:58:07Z | INFO  | [ Complete ] dest=/tmp/tmpspxw21ja/weights size="172 MB" total_elapsed=0.219s url=https://replicate.delivery/xezq/87BPGvMSmNIbHZdofe7mNpMHqh1I90yOm5mhEXhfZkpLsSFqA/flux-lora.tar
Downloaded weights in 0.28s
free=24187242397696
Downloading weights
2025-07-20T12:58:08Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpwnut1rgm/weights url=https://replicate.com/biggpt1/os-costume-male/_weights
2025-07-20T12:58:08Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-07-20T12:58:08Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.com/biggpt1/os-costume-male/_weights url=https://replicate.com/biggpt1/os-costume-male/_weights
2025-07-20T12:58:08Z | INFO  | [ Redirect ] redirect_url=https://replicate.delivery/xezq/4FvpgLtYfyye0kG5uQeZVIWJ8zRNf5PwMx41rm642utN4KJRB/trained_model.tar url=http://hermes.services.svc.cluster.local/replicate.com/biggpt1/os-costume-male/_weights
2025-07-20T12:58:11Z | INFO  | [ Complete ] dest=/tmp/tmpwnut1rgm/weights size="344 MB" total_elapsed=2.769s url=https://replicate.com/biggpt1/os-costume-male/_weights
Downloaded weights in 2.83s
Loaded LoRAs in 4.41s
Using seed: 7272
Prompt: Professional photoshoot of a TOK subject in cartoonish, cinematic cartoon style, set during a daring leap over a wild mountain river. Captured from a bold, cinematic angle: the camera is positioned low and close to the water, slightly behind and beneath the subject, on a dynamic diagonal that accentuates movement and scale. The perspective creates a sense of vertigo and immersion, as if the viewer is following the jump in real time. Wide shot.
The TOK subject, dressed in vivid traditional Ossetian attire—a striking red chokha (cherkeska) with decorative cartridges, crisp white shirt, black belt, and tall black boots—is caught mid-leap between mossy, towering boulders. Arms are flung wide for balance, body taut and athletic, the flowing fabric and sash trailing dramatically. His focus is intense, eyes locked forward on the landing rock, brows furrowed in determination and thrill.
Turbulent, foaming mountain water rushes beneath him, sparkling in the dawn light. The far bank is dotted with lush moss, delicate wildflowers, and weathered rocks. In the background, misty forested slopes and sweeping ridges frame the scene under a vivid morning sky.
The style is bold and cinematic: dramatic perspective, exaggerated sense of motion, dynamic lighting with streaks of sunlight cutting through cool mist, and painterly cartoon shading that enhances the epic, animated atmosphere.
Shot on a Canon R5 with a 24mm ultra-wide lens, using dramatic natural light and motion blur to amplify movement and immersion, perfect for a professional animated storyboard look.
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:01<00:28,  1.07s/it]
  7%|▋         | 2/28 [00:01<00:25,  1.01it/s]
 11%|█         | 3/28 [00:03<00:25,  1.02s/it]
 14%|█▍        | 4/28 [00:04<00:24,  1.04s/it]
 18%|█▊        | 5/28 [00:05<00:24,  1.05s/it]
 21%|██▏       | 6/28 [00:06<00:23,  1.06s/it]
 25%|██▌       | 7/28 [00:07<00:22,  1.07s/it]
 29%|██▊       | 8/28 [00:08<00:21,  1.07s/it]
 32%|███▏      | 9/28 [00:09<00:20,  1.07s/it]
 36%|███▌      | 10/28 [00:10<00:19,  1.07s/it]
 39%|███▉      | 11/28 [00:11<00:18,  1.07s/it]
 43%|████▎     | 12/28 [00:12<00:17,  1.07s/it]
 46%|████▋     | 13/28 [00:13<00:16,  1.08s/it]
 50%|█████     | 14/28 [00:14<00:15,  1.08s/it]
 54%|█████▎    | 15/28 [00:15<00:13,  1.07s/it]
 57%|█████▋    | 16/28 [00:17<00:12,  1.08s/it]
 61%|██████    | 17/28 [00:18<00:11,  1.08s/it]
 64%|██████▍   | 18/28 [00:19<00:10,  1.07s/it]
 68%|██████▊   | 19/28 [00:20<00:09,  1.07s/it]
 71%|███████▏  | 20/28 [00:21<00:08,  1.07s/it]
 75%|███████▌  | 21/28 [00:22<00:07,  1.07s/it]
 79%|███████▊  | 22/28 [00:23<00:06,  1.07s/it]
 82%|████████▏ | 23/28 [00:24<00:05,  1.07s/it]
 86%|████████▌ | 24/28 [00:25<00:04,  1.07s/it]
 89%|████████▉ | 25/28 [00:26<00:03,  1.07s/it]
 93%|█████████▎| 26/28 [00:27<00:02,  1.07s/it]
 96%|█████████▋| 27/28 [00:28<00:01,  1.08s/it]
100%|██████████| 28/28 [00:29<00:00,  1.08s/it]
100%|██████████| 28/28 [00:29<00:00,  1.07s/it]
Total safe images: 4 out of 4
Version Details
Version ID
6350aca7e72a57c8cb20e5256dc49c5ee32dc7155bead36e3bdd0fd0fa6ea41d
Version Created
July 20, 2025
Run on Replicate →