fofr/qwen-n74 🔢📝✓❓🖼️ → 🖼️

▶️ 13 runs 📅 Aug 2025 ⚙️ Cog 0.16.2
image-lora-training text-to-image

About

Example Output

Prompt:

"The Hyundai N Vision 74 car is driving fast along the golden gate bridge"

Output

Example output

Performance Metrics

48.58s Prediction Time
48.59s Total Time
All Input Parameters 
{
  "width": 512,
  "height": 512,
  "prompt": "The Hyundai N Vision 74 car is driving fast along the golden gate bridge",
  "go_fast": false,
  "guidance": 4,
  "image_size": "optimize_for_quality",
  "lora_scale": 1,
  "aspect_ratio": "16:9",
  "output_format": "webp",
  "enhance_prompt": false,
  "output_quality": 80,
  "negative_prompt": "",
  "num_inference_steps": 50
}
Input Parameters
seed Type: integer
Set a seed for reproducibility. Random by default.
width Type: integerRange: 512 - 2048
Custom width in pixels. Provide both width and height for custom dimensions (overrides aspect_ratio/image_size).
height Type: integerRange: 512 - 2048
Custom height in pixels. Provide both width and height for custom dimensions (overrides aspect_ratio/image_size).
prompt (required) Type: string
The main prompt for image generation
go_fast Type: booleanDefault: false
Use LCM-LoRA to accelerate image generation (trades quality for 8x speed)
guidance Type: numberDefault: 4Range: 0 - 10
Guidance scale for image generation. Defaults to 1 if go_fast, else 3.5.
image_size Default: optimize_for_quality
Image size preset (quality = larger, speed = faster). Ignored if width and height are both provided.
lora_scale Type: numberDefault: 1Range: 0 - 3
Scale for LoRA weights (0 = base model, 1 = full LoRA)
aspect_ratio Default: 16:9
Aspect ratio for the generated image. Ignored if width and height are both provided.
output_format Default: webp
Format of the output images
enhance_prompt Type: booleanDefault: false
Automatically enhance the prompt for better image generation
output_quality Type: integerDefault: 80Range: 0 - 100
Quality when saving images (0-100, higher is better, 100 = lossless)
negative_prompt Type: stringDefault:
Things you do not want to see in your image
replicate_weights Type: string
Path to LoRA weights file. Leave blank to use base model.
num_inference_steps Type: integerDefault: 50Range: 0 - 50
Number of denoising steps. More steps = higher quality. Defaults to 4 if go_fast, else 28.
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Missing keys: []
LoRA loaded: dim=64, alpha=64, scale=1.0
Generating: The Hyundai N Vision 74 car is driving fast along the golden gate bridge (1024x576, steps=50, seed=4107836538)
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:19,  2.48it/s]
  4%|▍         | 2/50 [00:00<00:18,  2.54it/s]
  6%|▌         | 3/50 [00:01<00:18,  2.55it/s]
  8%|▊         | 4/50 [00:01<00:17,  2.56it/s]
 10%|█         | 5/50 [00:01<00:17,  2.56it/s]
 12%|█▏        | 6/50 [00:02<00:17,  2.57it/s]
 14%|█▍        | 7/50 [00:02<00:18,  2.38it/s]
 16%|█▌        | 8/50 [00:03<00:20,  2.06it/s]
 18%|█▊        | 9/50 [00:04<00:21,  1.90it/s]
 20%|██        | 10/50 [00:04<00:22,  1.80it/s]
 22%|██▏       | 11/50 [00:05<00:22,  1.73it/s]
 24%|██▍       | 12/50 [00:05<00:22,  1.67it/s]
 26%|██▌       | 13/50 [00:06<00:22,  1.64it/s]
 28%|██▊       | 14/50 [00:07<00:20,  1.73it/s]
 30%|███       | 15/50 [00:07<00:18,  1.92it/s]
 32%|███▏      | 16/50 [00:07<00:16,  2.07it/s]
 34%|███▍      | 17/50 [00:08<00:15,  2.20it/s]
 36%|███▌      | 18/50 [00:08<00:13,  2.30it/s]
 38%|███▊      | 19/50 [00:09<00:13,  2.37it/s]
 40%|████      | 20/50 [00:09<00:12,  2.43it/s]
 42%|████▏     | 21/50 [00:09<00:11,  2.47it/s]
 44%|████▍     | 22/50 [00:10<00:11,  2.50it/s]
 46%|████▌     | 23/50 [00:10<00:10,  2.52it/s]
 48%|████▊     | 24/50 [00:11<00:10,  2.53it/s]
 50%|█████     | 25/50 [00:11<00:09,  2.54it/s]
 52%|█████▏    | 26/50 [00:11<00:09,  2.55it/s]
 54%|█████▍    | 27/50 [00:12<00:09,  2.41it/s]
 56%|█████▌    | 28/50 [00:12<00:10,  2.07it/s]
 58%|█████▊    | 29/50 [00:13<00:09,  2.11it/s]
 60%|██████    | 30/50 [00:13<00:08,  2.23it/s]
 62%|██████▏   | 31/50 [00:14<00:08,  2.32it/s]
 64%|██████▍   | 32/50 [00:14<00:07,  2.39it/s]
 66%|██████▌   | 33/50 [00:14<00:06,  2.44it/s]
 68%|██████▊   | 34/50 [00:15<00:06,  2.48it/s]
 70%|███████   | 35/50 [00:15<00:05,  2.51it/s]
 72%|███████▏  | 36/50 [00:16<00:05,  2.53it/s]
 74%|███████▍  | 37/50 [00:16<00:05,  2.54it/s]
 76%|███████▌  | 38/50 [00:16<00:04,  2.55it/s]
 78%|███████▊  | 39/50 [00:17<00:04,  2.55it/s]
 80%|████████  | 40/50 [00:17<00:03,  2.56it/s]
 82%|████████▏ | 41/50 [00:18<00:03,  2.56it/s]
 84%|████████▍ | 42/50 [00:18<00:03,  2.37it/s]
 86%|████████▌ | 43/50 [00:19<00:03,  1.96it/s]
 88%|████████▊ | 44/50 [00:19<00:03,  1.80it/s]
 90%|█████████ | 45/50 [00:20<00:02,  1.70it/s]
 92%|█████████▏| 46/50 [00:21<00:02,  1.63it/s]
 94%|█████████▍| 47/50 [00:21<00:01,  1.84it/s]
 96%|█████████▌| 48/50 [00:22<00:00,  2.01it/s]
 98%|█████████▊| 49/50 [00:22<00:00,  2.15it/s]
100%|██████████| 50/50 [00:22<00:00,  2.27it/s]
100%|██████████| 50/50 [00:22<00:00,  2.19it/s]
PREDICTION_TIME: 22.89 seconds
Generated: /tmp/output.webp
Version Details
Version ID
744737b83183da3fd6a271cf2c2fb5587161dbbdef4114fa0edcf9419f420049
Version Created
August 18, 2025
Run on Replicate →