fofr/qwen-tron-ares 🔢📝✓❓🖼️ → 🖼️

▶️ 11 runs 📅 Aug 2025 ⚙️ Cog 0.16.2

About

Qwen fine-tuned on TRON: ARES trailer

Example Output

Prompt:

"a screenshot from TRON_ARES, red"

Output

Performance Metrics

69.50s Prediction Time

95.20s Total Time

All Input Parameters

{
  "prompt": "a screenshot from TRON_ARES, red",
  "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

📐 Using quality preset for 16:9: 1664x928
create LoRA network. base dim (rank): 64, alpha: 64
neuron dropout: p=None, rank dropout: p=None, module dropout: p=None
create LoRA for Text Encoder: 0 modules.
create LoRA for U-Net: 840 modules.
enable LoRA for U-Net
Missing keys: []
LoRA loaded: dim=64, alpha=64, scale=1.0
Using random seed: 2591914231
Generating: a screenshot from TRON_ARES, red (1664x928, steps=50, seed=2591914231)
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:44,  1.11it/s]
  4%|▍         | 2/50 [00:01<00:40,  1.19it/s]
  6%|▌         | 3/50 [00:02<00:38,  1.21it/s]
  8%|▊         | 4/50 [00:03<00:37,  1.22it/s]
 10%|█         | 5/50 [00:04<00:41,  1.09it/s]
 12%|█▏        | 6/50 [00:05<00:38,  1.13it/s]
 14%|█▍        | 7/50 [00:06<00:36,  1.16it/s]
 16%|█▌        | 8/50 [00:06<00:35,  1.19it/s]
 18%|█▊        | 9/50 [00:07<00:34,  1.20it/s]
 20%|██        | 10/50 [00:08<00:33,  1.21it/s]
 22%|██▏       | 11/50 [00:09<00:31,  1.22it/s]
 24%|██▍       | 12/50 [00:10<00:31,  1.23it/s]
 26%|██▌       | 13/50 [00:10<00:30,  1.23it/s]
 28%|██▊       | 14/50 [00:11<00:29,  1.23it/s]
 30%|███       | 15/50 [00:12<00:28,  1.23it/s]
 32%|███▏      | 16/50 [00:13<00:27,  1.24it/s]
 34%|███▍      | 17/50 [00:14<00:26,  1.24it/s]
 36%|███▌      | 18/50 [00:14<00:25,  1.24it/s]
 38%|███▊      | 19/50 [00:15<00:25,  1.24it/s]
 40%|████      | 20/50 [00:16<00:24,  1.24it/s]
 42%|████▏     | 21/50 [00:17<00:23,  1.24it/s]
 44%|████▍     | 22/50 [00:18<00:22,  1.24it/s]
 46%|████▌     | 23/50 [00:18<00:21,  1.24it/s]
 48%|████▊     | 24/50 [00:19<00:20,  1.24it/s]
 50%|█████     | 25/50 [00:20<00:20,  1.24it/s]
 52%|█████▏    | 26/50 [00:21<00:19,  1.24it/s]
 54%|█████▍    | 27/50 [00:22<00:18,  1.24it/s]
 56%|█████▌    | 28/50 [00:22<00:17,  1.24it/s]
 58%|█████▊    | 29/50 [00:23<00:16,  1.24it/s]
 60%|██████    | 30/50 [00:24<00:16,  1.24it/s]
 62%|██████▏   | 31/50 [00:25<00:15,  1.24it/s]
 64%|██████▍   | 32/50 [00:26<00:14,  1.24it/s]
 66%|██████▌   | 33/50 [00:27<00:13,  1.24it/s]
 68%|██████▊   | 34/50 [00:27<00:12,  1.24it/s]
 70%|███████   | 35/50 [00:28<00:12,  1.24it/s]
 72%|███████▏  | 36/50 [00:29<00:11,  1.24it/s]
 74%|███████▍  | 37/50 [00:30<00:10,  1.24it/s]
 76%|███████▌  | 38/50 [00:31<00:09,  1.24it/s]
 78%|███████▊  | 39/50 [00:31<00:08,  1.24it/s]
 80%|████████  | 40/50 [00:32<00:08,  1.24it/s]
 82%|████████▏ | 41/50 [00:33<00:07,  1.24it/s]
 84%|████████▍ | 42/50 [00:34<00:06,  1.24it/s]
 86%|████████▌ | 43/50 [00:35<00:05,  1.24it/s]
 88%|████████▊ | 44/50 [00:35<00:04,  1.24it/s]
 90%|█████████ | 45/50 [00:36<00:04,  1.24it/s]
 92%|█████████▏| 46/50 [00:37<00:03,  1.24it/s]
 94%|█████████▍| 47/50 [00:38<00:02,  1.24it/s]
 96%|█████████▌| 48/50 [00:39<00:01,  1.24it/s]
 98%|█████████▊| 49/50 [00:39<00:00,  1.24it/s]
100%|██████████| 50/50 [00:40<00:00,  1.21it/s]
100%|██████████| 50/50 [00:40<00:00,  1.23it/s]
Generation took 41.57 seconds
Total safe images: 1/1

Version Details

Version ID: 3c6eeedc22dc09391eaca9b8abf0b4bf58ea8c9fa8ea674c30b46ba5fd970de0
Version Created: August 18, 2025

Run on Replicate →