cinemasetfree.com
fofr/qwen-2004
Qwen fine-tuned on bad photos from 2004
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
prompt * | string | The main prompt for image generation | — | — |
aspect_ratio | string | Aspect ratio for the generated image. Ignored if width and height are both provided. | "16:9" | 1:1 16:9 9:16 4:3 3:4 3:2 2:3 |
enhance_prompt | boolean | Automatically enhance the prompt for better image generation | false | — |
go_fast | boolean | Use LCM-LoRA to accelerate image generation (trades quality for 8x speed) | false | — |
guidance | number | Guidance scale for image generation. Defaults to 1 if go_fast, else 3.5. | 4 | min: 0, max: 10 |
height | integer | Custom height in pixels. Provide both width and height for custom dimensions (overrides aspect_ratio/image_size). | — | min: 512, max: 2048 |
image_size | string | Image size preset (quality = larger, speed = faster). Ignored if width and height are both provided. | "optimize_for_quality" | optimize_for_quality optimize_for_speed |
lora_scale | number | Scale for LoRA weights (0 = base model, 1 = full LoRA) | 1 | min: 0, max: 3 |
negative_prompt | string | Things you do not want to see in your image | "" | — |
num_inference_steps | integer | Number of denoising steps. More steps = higher quality. Defaults to 4 if go_fast, else 28. | 50 | min: 0, max: 50 |
output_format | string | Format of the output images | "webp" | webp jpg png |
output_quality | integer | Quality when saving images (0-100, higher is better, 100 = lossless) | 80 | min: 0, max: 100 |
replicate_weights | string (uri) | Path to LoRA weights file. Leave blank to use base model. | — | — |
seed | integer | Set a seed for reproducibility. Random by default. | — | — |
width | integer | Custom width in pixels. Provide both width and height for custom dimensions (overrides aspect_ratio/image_size). | — | min: 512, max: 2048 |
prompt required string The main prompt for image generation
aspect_ratio string Aspect ratio for the generated image. Ignored if width and height are both provided.
"16:9" enhance_prompt boolean Automatically enhance the prompt for better image generation
false go_fast boolean Use LCM-LoRA to accelerate image generation (trades quality for 8x speed)
false guidance number Guidance scale for image generation. Defaults to 1 if go_fast, else 3.5.
4 min: 0, max: 10 height integer Custom height in pixels. Provide both width and height for custom dimensions (overrides aspect_ratio/image_size).
image_size string Image size preset (quality = larger, speed = faster). Ignored if width and height are both provided.
"optimize_for_quality" lora_scale number Scale for LoRA weights (0 = base model, 1 = full LoRA)
1 min: 0, max: 3 negative_prompt string Things you do not want to see in your image
"" num_inference_steps integer Number of denoising steps. More steps = higher quality. Defaults to 4 if go_fast, else 28.
50 min: 0, max: 50 output_format string Format of the output images
"webp" output_quality integer Quality when saving images (0-100, higher is better, 100 = lossless)
80 min: 0, max: 100 replicate_weights string Path to LoRA weights file. Leave blank to use base model.
seed integer Set a seed for reproducibility. Random by default.
width integer Custom width in pixels. Provide both width and height for custom dimensions (overrides aspect_ratio/image_size).
926f5860c353 Updated: 2/26/2026 70 runs