You're looking at a specific version of this model. Jump to the model overview.
joyanujoy /analog_diffusion:02ffc3c9
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
|
a photo of <1> riding a horse on mars
|
Input prompt. Use <1>, <2>, <3>, etc., to specify LoRA concepts
|
| negative_prompt |
string
|
|
Specify things to not see in the output
|
| width |
integer
(enum)
|
512
Options: 128, 256, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960, 1024 |
Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
|
| height |
integer
(enum)
|
512
Options: 128, 256, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960, 1024 |
Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to output.
|
| num_inference_steps |
integer
|
50
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
7.5
Min: 1 Max: 20 |
Scale for classifier-free guidance
|
| image |
string
|
(Img2Img) Inital image to generate variations of. If this is not none, Img2Img will be invoked.
|
|
| remove_background |
boolean
|
True
|
Automatically remove background from above Img2Img initial image.
|
| clip_interrogator |
boolean
|
True
|
Generate prompt from init image. Generated prompt will override manually entered text prompt input
|
| prompt_strength |
number
|
0.8
|
(Img2Img) Prompt strength when providing the image. 1.0 corresponds to full destruction of information in init image
|
| scheduler |
string
(enum)
|
DPMSolverMultistep
Options: DDIM, K_EULER, DPMSolverMultistep, K_EULER_ANCESTRAL, PNDM, KLMS |
Choose a scheduler.
|
| lora_urls |
string
|
|
List of urls for safetensors of lora models, seperated with | .
|
| lora_scales |
string
|
0.5
|
List of scales for safetensors of lora models, seperated with |
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| adapter_condition_image |
string
|
(T2I-adapter) Adapter Condition Image to gain extra control over generation. If this is not none, T2I adapter will be invoked.
|
|
| adapter_type |
string
(enum)
|
sketch
Options: sketch, seg, keypose, depth |
(T2I-adapter) Choose an adapter type for the additional condition.
|
| upscale |
integer
(enum)
|
Options: 2, 4, 8 |
Upscaling factor
|
| verbose_response |
boolean
|
False
|
Return a response object with detail info. Prompt, seed used etc.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'properties': {'adapter_type': {'title': 'Adapter Type', 'type': 'string'},
'clip_interrogator': {'title': 'Clip Interrogator'},
'guidance_scale': {'title': 'Guidance Scale', 'type': 'number'},
'height': {'title': 'Height', 'type': 'integer'},
'images': {'default': [],
'items': {'format': 'uri', 'type': 'string'},
'title': 'Images',
'type': 'array'},
'negative_prompt': {'title': 'Negative Prompt',
'type': 'string'},
'num_inference_steps': {'title': 'Num Inference Steps',
'type': 'integer'},
'prompt': {'title': 'Prompt', 'type': 'string'},
'prompt_strength': {'title': 'Prompt Strength'},
'remove_background': {'title': 'Remove Background'},
'scheduler': {'title': 'Scheduler', 'type': 'string'},
'seed': {'title': 'Seed', 'type': 'integer'},
'upscale': {'title': 'Upscale'},
'width': {'title': 'Width', 'type': 'integer'}},
'title': 'Output',
'type': 'object'}