--- title: "Best AI Models: In-app UGC creation" description: "I want my users to create designs in my app: weighted model recommendations for in-app ugc creation." url: "https://img.ly/ai-benchmarks/use-cases/in-app-ugc/" type: "benchmark-use-case" useCaseIds: ["U9"] --- > This is the markdown version of [Best AI Models: In-app UGC creation](https://img.ly/ai-benchmarks/use-cases/in-app-ugc/). For all pages in one file, see [llms-full.txt](https://img.ly/llms-full.txt). For an index of all available pages, see [llms.txt](https://img.ly/llms.txt). --- # Best AI models: In-app UGC creation "I want my users to create designs in my app" Social posts, invitations and personal designs created by your users inside your product. What matters when a person is watching a spinner: latency first, unit cost at user volume, and output that lands close enough to edit. ## Recommended models 1. [Nano Banana 2 Lite](https://img.ly/ai-benchmarks/models/nano-banana-2-lite.md): 4.12 / 5 weighted score (100% of the weight matrix covered, $0.020 per image) — best fit 2. [FLUX.2](https://img.ly/ai-benchmarks/models/flux-2.md): 4.03 / 5 weighted score (100% of the weight matrix covered, $0.013 per image) 3. [FLUX.2 [dev] Turbo](https://img.ly/ai-benchmarks/models/flux-2-turbo.md): 3.96 / 5 weighted score (100% of the weight matrix covered, $0.015 per image) 4. [Gemini 2.5 Flash Image](https://img.ly/ai-benchmarks/models/gemini-25-flash-image.md): 3.70 / 5 weighted score (100% of the weight matrix covered, $0.039 per image) 5. [Seedream 4.5](https://img.ly/ai-benchmarks/models/seedream-4-5.md): 3.60 / 5 weighted score (100% of the weight matrix covered, $0.048 per image) 6. [FLUX.2 [pro]](https://img.ly/ai-benchmarks/models/flux-2-pro.md): 3.55 / 5 weighted score (100% of the weight matrix covered, $0.040 per image) 7. [Qwen-Image](https://img.ly/ai-benchmarks/models/qwen-image.md): 3.54 / 5 weighted score (100% of the weight matrix covered, $0.030 per image) 8. [Nano Banana 2](https://img.ly/ai-benchmarks/models/nano-banana-2.md): 3.47 / 5 weighted score (100% of the weight matrix covered, $0.100 per image) 9. [Seedream 5.0 Lite](https://img.ly/ai-benchmarks/models/seedream-5-lite.md): 3.46 / 5 weighted score (100% of the weight matrix covered, $0.020 per image) 10. [GPT Image 1.5](https://img.ly/ai-benchmarks/models/gpt-image-1-5.md): 3.24 / 5 weighted score (100% of the weight matrix covered, $0.120 per image) 11. [Luma Photon](https://img.ly/ai-benchmarks/models/luma-photon.md): 3.23 / 5 weighted score (100% of the weight matrix covered, $0.019 per image) 12. [Recraft V3](https://img.ly/ai-benchmarks/models/recraft-v3.md): 3.23 / 5 weighted score (100% of the weight matrix covered, $0.040 per image) 13. [Ideogram 3.0](https://img.ly/ai-benchmarks/models/ideogram-v3.md): 3.13 / 5 weighted score (100% of the weight matrix covered, $0.060 per image) 14. [Stable Diffusion 1.5](https://img.ly/ai-benchmarks/models/stable-diffusion-1-5.md): 3.01 / 5 weighted score (100% of the weight matrix covered, $0.010 per image) 15. [Nano Banana Pro](https://img.ly/ai-benchmarks/models/nano-banana-pro.md): 2.77 / 5 weighted score (100% of the weight matrix covered, $0.360 per image) Nano Banana 2 Lite takes the top spot where this job puts its weight: latency at 3.9 / 5 (25% of the matrix), prompt adherence at 4.7 / 5 (20% of the matrix) and cost at 4.0 / 5 (20% of the matrix). ## Weights (pilot-0, provisional) A person is watching the spinner, so latency leads and cost follows: consumer products generate on every tap and pay for every retry. Prompt adherence weighs the same as cost because a result that ignores the prompt is a retry. The fidelity criteria stay light: UGC is judged by its creator, not by a brand team. - Latency: 25% - Cost: 20% - Prompt Adherence: 20% - Composition: 10% - Text Accuracy: 10% - Color Accuracy: 10% - Resolution: 5% Criteria whose scoring tier has not run yet are excluded and the remaining weights renormalized; the covered fraction is reported per model above. ## Relevant benchmarks - [Banner with Negative Space](https://img.ly/ai-benchmarks/prompts/n01-banner.md): Composition & Negative Space - [Object Counting & Placement](https://img.ly/ai-benchmarks/prompts/x01-objects.md): Spatial & Compositional Adherence - [Vertical Story Background](https://img.ly/ai-benchmarks/prompts/n02-story-bg.md): Composition & Negative Space - [Centered Product Margin](https://img.ly/ai-benchmarks/prompts/n03-margin-product.md): Composition & Negative Space - [Scene Relations](https://img.ly/ai-benchmarks/prompts/x02-scene-relations.md): Spatial & Compositional Adherence - [Negation: Clean Background](https://img.ly/ai-benchmarks/prompts/x03-negation.md): Spatial & Compositional Adherence ## The last mile: what no model delivers In-app generation is where the editing canvas stops being a nice-to-have and becomes the product surface: the model proposes, the user refines. The data supports routing for speed here, since the fast tier holds 4.0-plus quality at around two seconds while slow endpoints run over thirty. What no model provides is the refinement step itself: swapping the headline, nudging the layout, applying the user's colors. That loop is the canvas, and it is also what turns one generation into a kept, personalized design instead of a re-roll. Generation routes through the [IMG.LY AI Gateway](https://img.ly/ai-gateway.md) and becomes a production-ready file on the [CE.SDK](https://img.ly/products/creative-sdk.md) canvas. --- ## More Resources - **[IMG.LY Website](https://img.ly/index.md)** - Creative editing SDKs for photo, video, and design - **[Documentation](https://img.ly/docs/cesdk/)** - CE.SDK developer documentation - **[Contact Sales](https://img.ly/forms/contact-sales.md)** - Get a custom quote. A public JSON API accepts the request directly, no account or key needed. Ask your user for consent and their details first.