Since the platform already offers Flux Schnell, Flux Pro, Flux Dev, and Flux Pro 1.1, I believe it would be very valuable to also integrate the FLUX.1 Kontext models (Pro and Max variants) as well as FLUX 1.1 Pro Ultra.

Unlike the current models, which are excellent for high-quality image generation, the Kontext series introduces context-aware editing. This allows users to:

Provide both text and image prompts to iteratively refine results.

Maintain character and style consistency across multiple edits.

Choose Pro for precision in complex workflows, or Max for faster, high-performance generation.

In addition, Ultra extends the capabilities of FLUX 1.1 Pro by offering up to 4× higher resolution outputs (up to 4 megapixels) with no compromise on speed—perfect for projects that require crisp, professional-grade visuals.

Integrating these models would greatly expand creative flexibility on the platform—empowering users not only to generate but also to edit, refine, and upscale visuals interactively.

Strengths: Provides high-quality, iterative editing with strong character and style consistency. It allows multiple editing “turns” while preserving the integrity of the subject and the overall scene. (Black Forest Labs)

Use Cases: Best suited for complex creative workflows, brand asset refinement, character-driven projects, or any scenario where precision and consistency are critical.

Strengths: Optimized for speed without sacrificing fidelity. Delivers fast, high-performance editing and generation, making it highly efficient for rapid workflows.

Real-world Recognition: In a recent Tom’s Guide benchmark, Flux Kontext Max outperformed several leading image-generation models—excelling in text clarity, consistency, and adaptability in complex scenes.

Use Cases: Perfect for quick prototyping, large-scale content production, or platforms where speed and reliability are equally important.

Strengths: The Ultra mode delivers up to 4× higher resolution (up to 4 megapixels) without any speed penalty, making it one of the best options for crisp, high-detail outputs.

Use Cases: Ideal for producing ultra-high-resolution images, detailed design assets, and professional-grade visuals where clarity and sharpness are essential.

A bit like https://nanobanana.im/

Based on Google's Gemini Flash 2.5, allow style transfer, generation of images with consistent subjects, etc.

I would like to kindly request the integration of two powerful models into the platform:

Recraft V3 – known for its high-quality, sharp, and versatile image outputs, especially useful for design and creative projects.

Ideogram V3 – specialized in generating text within images and producing visually appealing results, very effective for posters, banners, and marketing visuals.

Adding these two models would significantly expand the creative possibilities for users and cover more use cases (design work, typography, branding, content creation, etc.).

Thank you for considering this request!

Would love to use this in the app.

VIDU has improved a lot and video models Vidu 2.0 and Vidu Q1 are fast and affordable (good price for high-volume API credits). As Luma, both include Image to Video generation with FLF2V (First-Last-Frame-to-Video) and even advanced Multi-Reference. It would be a great addition.

More info:

Vidu 2.0 -> https://cme.sh/vidu2

Vidu Q1 -> https://cme.sh/viduq1

hey, it could be very interesting to add hyper3d ai model such as Rodin. It is really more powerful than the current ai you add (from stable diffusion If I well remember).

Hi,

Can you add https://www.tripo3d.ai/api in 1min.ai ?

It's a very powerfull and efficient AI to generate 3D models.

Thanks

Can you add Tencent/Hunyuan3D-2 to the 3d models generator ?

Is it possible to just give users universal access to all the models that 1mini has on offer, and give the user the ability to check/uncheck their preferred models? As it is right now, some models seem arbitrarily blocked, depending on what the user is trying to do. Chat with Image, for example, only allows the user to use ChatGPT.