You're looking at a specific version of this model. Jump to the model overview.
sergeishapovalov /forge:44bedb22
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
Prompt
|
|
| negative_prompt |
string
|
|
Negative Prompt (для Flux рекомендуется оставить пустым и использовать Distilled CFG)
|
| width |
integer
|
768
Min: 1 Max: 1280 |
Width of output image
|
| height |
integer
|
1280
Min: 1 Max: 1280 |
Height of output image
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to output
|
| sampler |
None
|
[Forge] Flux Realistic
|
Sampling method для Flux моделей
|
| scheduler |
None
|
Simple
|
Schedule type для Flux моделей
|
| num_inference_steps |
integer
|
15
Min: 1 Max: 50 |
Number of denoising steps
|
| guidance_scale |
number
|
1
Min: 1 Max: 50 |
CFG Scale (для Flux рекомендуется значение 1.0)
|
| distilled_guidance_scale |
number
|
3.5
Max: 30 |
Distilled CFG Scale (основной параметр для Flux, рекомендуется 3.5)
|
| seed |
integer
|
-1
|
Random seed. Leave blank to randomize the seed
|
| enable_hr |
boolean
|
False
|
Hires. fix
|
| hr_upscaler |
None
|
Latent
|
Upscaler for Hires. fix
|
| hr_steps |
integer
|
20
Max: 100 |
Inference steps for Hires. fix
|
| hr_scale |
number
|
2
Min: 1 Max: 4 |
Factor to scale image by
|
| denoising_strength |
number
|
0.5
Max: 1 |
Denoising strength. 1.0 corresponds to full destruction of information in init image
|
| enable_adetailer |
boolean
|
False
|
ADetailer (не рекомендуется для Flux моделей)
|
| lora_urls |
string
|
|
Ссылки на LoRA файлы, разделенные запятыми (например, https://example.com/lora1.safetensors,https://example.com/lora2.safetensors)
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}