Stable diffusion with the ability to change checkpoint, still wip.

You can use cURL or any other http client to run inferences:

```bash
curl -X POST \
    -d '{"input": {"model": "..."}}'  \
    -H 'Content-Type: application/json'  \
    -H "Authorization: bearer $(deepctl auth token)"  \
    'https://api.deepinfra.com/v1/inference/$MODEL'
```

The inpu/output is compatible with the cog interface.


You can use our command-line tool [deepctl](/docs/getting-started) to run
inferences:

```bash
deepctl infer \
    -m '$MODEL'  \
    -i model=...  \
    -i vae=...  \
    -i prompt=...
```


model

prompt

The negative prompt (For things you don't want)

negative_prompt

sampler_name

steps

CFG Scale defines how much attention the model pays to the prompt when generating

cfg_scale

width

height

batch_size

enable_hr

hr_scale

The seed used when generating, set to -1 for random seed

seed

Batch Size

Cfg Scale

Enable Hr

Height

Hr Scale

Negative Prompt

Prompt

Seed

Steps

Width

Input

Output

uwulewd/custom-diffusion

HTTP/cURL API

Input fields

`model`string

`vae`string

`prompt`string

`negative_prompt`string

`sampler_name`string

`steps`integer

`cfg_scale`number

`width`integer

`height`integer

`batch_size`integer

`enable_hr`boolean

`hr_scale`integer

`seed`integer

Input Schema

Output Schema

uwulewd/custom-diffusion

HTTP/cURL API

Input fields

modelstring

vaestring

promptstring

negative_promptstring

sampler_namestring

stepsinteger

cfg_scalenumber

widthinteger

heightinteger

batch_sizeinteger

enable_hrboolean

hr_scaleinteger

seedinteger