Enum ImageModel 

#[non_exhaustive]
pub enum ImageModel {
    DallE2,
    DallE3,
    GptImage1,
    GptImage1Mini,
    GptImage1_5,
    GptImage2,
    GptImage2_5Flare,
    GptImage2_5Sunburst,
    ChatGptImageLatest,
}

Image generation models.

DALL-E retirement

OpenAI retired dall-e-2 and dall-e-3 on api.openai.com - requests naming them fail with “The model ‘dall-e-3’ does not exist.” The variants are kept because Azure OpenAI deployments can still serve DALL-E, but new OpenAI code should use one of the GPT Image models.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

DallE2

DALL-E 2 model - supports variations, smaller sizes

Retired on OpenAI; may still exist as an Azure deployment.

DallE3

DALL-E 3 model - higher quality, HD support, style options

Retired on OpenAI; may still exist as an Azure deployment.

GptImage1

GPT Image model - latest generation (default)

GptImage1Mini

GPT Image 1 Mini - cheaper gpt-image-1 for high-volume generation

GptImage1_5

GPT Image 1.5 - refreshed gpt-image-1

GptImage2

GPT Image 2 - state-of-the-art generation and editing

GptImage2_5Flare

GPT Image 2.5 Flare - fast, everyday image generation and editing

Has approximately 50% lower latency than GPT Image 2. It has the same pricing as GPT Image 2.5 Sunburst.

Accepts low, medium, high, auto, and max quality, but rejects DALL-E’s standard and hd values. Although max is accepted, API validation errors only list low, medium, high, and auto. response_format and style are unknown parameters and responses are always base64. The API accepts output_format: webp and background: transparent.

GptImage2_5Sunburst

GPT Image 2.5 Sunburst - generation and finely controlled editing

Has the same pricing as GPT Image 2.5 Flare. At max quality, one generation can take more than 60 seconds; configure a longer timeout when using request timeouts.

Accepts low, medium, high, auto, and max quality, but rejects DALL-E’s standard and hd values. Although max is accepted, API validation errors only list low, medium, high, and auto. response_format and style are unknown parameters and responses are always base64. The API accepts output_format: webp and background: transparent.

ChatGptImageLatest

ChatGPT Image Latest - image model currently used in ChatGPT

Requires a verified organization.

Implementations

impl ImageModel

pub fn as_str(&self) -> &'static str

Returns the model identifier string.

Trait Implementations

impl Clone for ImageModel

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for ImageModel

impl Debug for ImageModel

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ImageModel

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ImageModel

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for ImageModel

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Eq for ImageModel

impl PartialEq for ImageModel

fn eq(&self, other: &Self) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl Serialize for ImageModel

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ImageModel