yosun/camcorgi-qwern 🔢📝✓❓🖼️ → 🖼️

▶️ 9 runs 📅 Aug 2025 ⚙️ Cog 0.16.2
image-consistent-character-generation text-to-image

About

a qwen lora that knows that CAM corgi looks like... https://replicate.delivery/xezq/Qeh4prhrfEjLOEoB2kgdzS98yArm2SoruIPG8mkV3TLoHYNVA/qwen_lora_1755827163_trained.zip

Example Output

Prompt:

"a photo of of CAM corgi in san francisco"

Output

Example output

Performance Metrics

39.87s Prediction Time
39.91s Total Time
All Input Parameters 
{
  "prompt": "a photo of of CAM corgi  in san francisco",
  "go_fast": true,
  "guidance": 4,
  "image_size": "optimize_for_speed",
  "lora_scale": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "enhance_prompt": true,
  "output_quality": 80,
  "negative_prompt": "",
  "num_inference_steps": 20
}
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 speed preset for 1:1: 1024x1024
Missing keys: []
LoRA loaded: dim=64, alpha=64, scale=1.0
Using random seed: 911540456
Generating: a photo of of CAM corgi  in san francisco, highly detailed, crisp focus, studio lighting, photorealistic (1024x1024, steps=20, seed=911540456)
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:10,  1.74it/s]
 10%|█         | 2/20 [00:01<00:10,  1.74it/s]
 15%|█▌        | 3/20 [00:01<00:09,  1.75it/s]
 20%|██        | 4/20 [00:02<00:09,  1.75it/s]
 25%|██▌       | 5/20 [00:02<00:08,  1.75it/s]
 30%|███       | 6/20 [00:03<00:08,  1.74it/s]
 35%|███▌      | 7/20 [00:04<00:07,  1.74it/s]
 40%|████      | 8/20 [00:04<00:06,  1.75it/s]
 45%|████▌     | 9/20 [00:05<00:06,  1.74it/s]
 50%|█████     | 10/20 [00:05<00:05,  1.75it/s]
 55%|█████▌    | 11/20 [00:06<00:05,  1.75it/s]
 60%|██████    | 12/20 [00:06<00:04,  1.75it/s]
 65%|██████▌   | 13/20 [00:07<00:04,  1.75it/s]
 70%|███████   | 14/20 [00:08<00:03,  1.74it/s]
 75%|███████▌  | 15/20 [00:08<00:02,  1.74it/s]
 80%|████████  | 16/20 [00:09<00:02,  1.74it/s]
 85%|████████▌ | 17/20 [00:09<00:01,  1.74it/s]
 90%|█████████ | 18/20 [00:10<00:01,  1.75it/s]
 95%|█████████▌| 19/20 [00:10<00:00,  1.75it/s]
100%|██████████| 20/20 [00:11<00:00,  1.75it/s]
100%|██████████| 20/20 [00:11<00:00,  1.75it/s]
Generation took 11.60 seconds
Total safe images: 1/1
Version Details
Version ID
4b3450a5bc9f4655c0ba6a5c168126e15c8199aae66cd543cfe8731de3c05f8f
Version Created
August 22, 2025
Run on Replicate →