AI Text to Image: Illustrations, Posters and Concepts · TelkNet

Image generationGPU workloadideogram4 · Source ideogram-4-nf4 · Weights ideogram-4-fp8 · Weights

Image generation

Describe the subject, composition, lighting and visible text, then choose a model, canvas size and image count. Generate illustrations, posters or product concepts, preview each PNG and download it. Check lettering and fine details in the result.

5-600 credits/useText promptEstimated 600-10800 seconds

Input

Prompt, width, height, sampler preset, and seed

Output

PNG images generated with Ideogram 4 NF4.

Use case

Text-sensitive posters, covers, logos, packaging, product visuals, and structured design concepts

Choose a model family

Krea 2 image generationUnder MaintenanceFast text-to-image exploration, moodboards, product concepts, editorial visuals, and creative draftsIdeogram 4 image generationUnder MaintenanceText-sensitive posters, covers, logos, packaging, product visuals, and structured design concepts

Choose a model for your material and purpose, and review the examples before submitting.

Cost, time, formats and parameters depend on the selected model.

Under Maintenance

This tool is under maintenance. Please try again later.

Quick feedback

Include the tool name, steps and the problem in your feedback. Screenshots can help us locate it.

Models, parameters, and sources

Text-sensitive posters, covers, logos, packaging, product visuals, and structured design concepts

Krea 2 TurboIdeogram 4Krea 2Krea 2 open-source releaseKrea image generatorKrea text to imageKrea open weightsKrea 2 open-weight TurboKrea 2 Turbo 8 stepaesthetic image generationAI moodboard generatorfast image brainstorming

Krea 2 Turbo

Krea 2 Turbo is the official 8-step distilled open-weight checkpoint Krea recommends for daily inference.

krea/Krea-2-Turbo krea/Krea-2-Raw krea-ai/krea-2 Krea 2 open-source release Krea 2 technical report Krea 2 prompting guide

Krea 2 Turbo official inference settings are 8 steps, CFG 0.0, and mu 1.15.
The release describes a 12B dense DiT with Qwen Image VAE and Qwen3-VL text encoder components.
Krea 2 Turbo is an open-weight release under the Krea community license.
The official prompting guide recommends natural-language prompts, detailed composition, and quoting rendered text; Krea is better for fast aesthetic exploration than for replacing Ideogram 4 structured typography and layout control.

Ideogram 4 NF4

Ideogram 4 NF4 is the 9.3B open-weight text-to-image foundation model path used here for design, typography, structured prompts, bbox layout control, and native 2K generation.

ideogram-oss/ideogram4 Ideogram 4 model page Ideogram 4 technical blog ideogram-ai/ideogram-4-nf4 ideogram-ai/ideogram-4-fp8

The official model card describes Ideogram 4 as an open-weight image model at the frontier of design, and ranks it first among open-weight models on Design Arena.
Current weights: TelkNet uses ideogram-ai/ideogram-4-nf4. This is the official public NF4 quantized weight path, not a full-precision checkpoint; an FP8 variant is also available for evaluation.
Prompt control: the official path supports structured JSON prompts, visible text, bbox coordinate layout, color, and style controls for posters, brand work, packaging, and product visuals.
Text strength: the official model card emphasizes multilingual text rendering, signage, logos, titles, watermarks, and multi-line text as core strengths of Ideogram 4.
Official highest-quality recommendation: V4 Quality 48 with an explicit canvas up to 2048x2048.

Model comparison

Model

Role

Why it is used

Output impact

ModelKrea 2 Turbo

krea/Krea-2-Turbo

RoleDaily inference path

Why it is usedKrea 2 Turbo official inference settings are 8 steps, CFG 0.0, and mu 1.15.

Output impactPNG image candidates from the Turbo checkpoint with the official 8-step settings.

ModelIdeogram 4

Ideogram 4 tool ideogram-ai/ideogram-4-nf4

RoleTypography and design comparison

Why it is usedIdeogram 4 can be better for exact text rendering, logos, packaging, bbox layouts, and poster typography.

Output impactUse the quick link when visible text and layout control are more important than general image Elo.

ModelIdeogram 4 nf4

ideogram-ai/ideogram-4-nf4 ideogram-oss/ideogram4

RoleImage generation model used on TelkNet

Why it is usedPNG images generated with Ideogram 4 NF4.

Output impactPNG image

ModelIdeogram 4 fp8

ideogram-ai/ideogram-4-fp8 ideogram-oss/ideogram4

RoleOfficial alternate quantization

Why it is usedFP8 quantization variant; image generation on TelkNet uses NF4.

Output impactReference variant

ModelOther open-weight image models

ideogram-ai/ideogram-4-nf4 Ideogram 4 technical blog

RoleExternal model context

Why it is usedThe technical blog describes the 9.3B single-stream DiT architecture, Qwen3-VL text encoder, and structured prompting design.

Output impactRanking context

Paper and benchmark notes

This checkpoint has no reproducible public score table. See the linked release material for details.

Ideogram 4

Paper and benchmark notes

Krea 2

GitHub release - 2026

The Krea 2 repository documents the Raw open-weight checkpoint, inference guidance, and local usage.

krea-ai/krea-2 Krea 2 Turbo Krea 2 Raw Technical report

Krea 2 open-source release

Krea release page - 2026

The Krea release page describes the Raw open-weight release and architecture components.

Release page Krea 2 Turbo Krea 2 Raw Prompting guide

Ideogram 4

Hugging Face model card - 2026

The official Ideogram 4 model card documents NF4/FP8 variants, benchmarks, structured prompting, 2048 support, and recommended sampler settings.

ideogram-4-nf4

Ideogram 4.0 Technical Details

Ideogram technical blog - 2026

The technical blog describes the 9.3B single-stream DiT architecture, Qwen3-VL text encoder, and structured prompting design.

Technical blog Official inference repository ideogram-4-fp8 Model page

Official / repositories

krea/Krea-2-Turbo krea/Krea-2-Raw krea-ai/krea-2 Krea 2 open-source release Krea 2 technical report Krea 2 prompting guide ideogram-oss/ideogram4 Ideogram 4 model page Ideogram 4 technical blog ideogram-ai/ideogram-4-nf4 ideogram-ai/ideogram-4-fp8

Papers / technical notes

No paper links are provided.

Parameter guide

Prompt: describes the image subject, visible text, layout, and design style.
Width: official range 256-2048px, in multiples of 16.
Height: official range 256-2048px, in multiples of 16, with aspect ratio from 1:6 to 6:1.
Sampler preset: V4 Quality 48 is the official quality-oriented default.
Seed: 0 uses TelkNet's stable automatic seed; click the dice for a random explicit seed.

Use cases

Generate design concepts from detailed prompts
Draft posters or covers with readable titles, logo-like text, and layout
Explore structured references for products, brands, packaging, or interfaces

Workflow

1Write the prompt and set any official width and height
2Choose the canvas size, quality preset and image count, then submit.
3Download every generated PNG from the completed task

What to check

Specify visible text, bbox layout, colors, and style clearly
Choose the canvas size, quality preset and image count, then submit.
Seed 0 uses TelkNet stable auto-seeding; use the dice control to set an explicit random seed

Models in this field

7 entries

Includes public test results for models used here and elsewhere. The complete source table is shown by default; conditions and metrics can also be selected for comparison. Scores from different test conditions are not directly comparable.

Only records with verified public inference implementations and matching weights are shown; algorithms requiring no weights are also eligible. Closed services, unreleased weights and unmatched experiment versions are excluded. This is not an all-model leaderboard.

Public weights do not establish a fully open-source license. Expand the data for declared weight licenses and access conditions. Undeclared licenses are marked separately.

BenchmarkRanking category

The selected model has no verified matching public result and has not been ranked.

SenseNova-U1 official model card

Choose a dataset to view all metrics for each model. Rows follow the official rank or selected metric. Bold marks each column’s best comparable value, including ties. Different evaluation protocols are ranked separately; missing scores are shown as -.

Deployable entries 7 / source rows 12

Not ranked: 5

A complete public inference package for these experiments has not been verified. Other weights with the same model name do not qualify.

Nano-Banana-Pro · Commercial Models · Nano-Banana-2.0 · Commercial Models · GPT-Image-1.5 · Commercial Models · Qwen-Image-2.0 · Commercial Models · Seedream-4.5 · Commercial Models

This benchmark covers infographic generation, not general image generation.

Rank by metric

SenseNova-U1 official model card
Metric rank	Model	Test setting	BizGenEval Avg. (hard / easy) ↑	IGenBench Q-ACC ↑	IGenBench I-ACC ↑	OneIG(EN) ↑	OneIG(ZH) ↑
1	SenseNova-U1-8B-MoT-Infographic-V2 Public weights · Inference code sensenova/SenseNova-U1-8B-MoT-Infographic-V2@c10505236bc9d655cfabbe62e3457a5ccf40b7d9 Inference code Weight license (repository declaration): apache-2.0	Open-source Models	50.3 / 67.9	71.4	18.3	55.4	53.5
2	SenseNova-U1-8B-MoT-Infographic Public weights · Inference code sensenova/SenseNova-U1-8B-MoT-Infographic@31a83a0dd3f5ec352688b5df62add01ca4584695 Inference code Evaluation settings Weight license (repository declaration): apache-2.0	Open-source Models	46.6 / 65.4	69.5	17.0	55.6	53.3
3	SenseNova-U1-8B-MoT Public weights · Inference code sensenova/SenseNova-U1-8B-MoT@bfa9b436503cb8aed4f2bc60e3236710cc77468d Inference code Evaluation settings Weight license (repository declaration): apache-2.0	Open-source Models	39.8 / 61.1	51.3	4.2	54.5	53.8
4	Qwen-Image Public weights · Inference code Qwen/Qwen-Image@75e0b4be04f60ec59a75f475837eced720f823b6 Inference code Evaluation settings Weight license (repository declaration): apache-2.0	Open-source Models	2.8 / 23.8	36.0	0.0	53.9	54.8
5	Qwen-Image-2512 Public weights · Inference code Qwen/Qwen-Image-2512@25468b98e3276ca6700de15c6628e51b7de54a26 Inference code Weight license (repository declaration): apache-2.0	Open-source Models	6.3 / 41.0	32.2	1.0	53.0	51.5
6	Z-Image Public weights · Inference code Tongyi-MAI/Z-Image@04cc4abb7c5069926f75c9bfde9ef43d49423021 Inference code Weight license (repository declaration): apache-2.0	Open-source Models	8.2 / 43.8	30.0	1.0	54.6	53.5
7	Bagel Public weights · Inference code ByteDance-Seed/BAGEL-7B-MoT@5019f57d168e5816e8f3f701b17cc816bb7cf24b Inference code Evaluation settings Weight license (repository declaration): apache-2.0	Open-source Models	2.0 / 3.7	4.9	0.0	36.1	37.0

Original records (7)

SenseNova-U1 official model card ↗Checked: 2026-10-25

All evaluation sources (1)

Datasets, versions and conditions remain separate, including sources with no eligible ranking rows.

SenseNova-U1 official model card ↗
Deployable entries 7 / source rows 12
Not ranked: 5
A complete public inference package for these experiments has not been verified. Other weights with the same model name do not qualify.
Nano-Banana-Pro · Commercial Models · Nano-Banana-2.0 · Commercial Models · GPT-Image-1.5 · Commercial Models · Qwen-Image-2.0 · Commercial Models · Seedream-4.5 · Commercial Models

Related use-case guides

Find processing methods and steps suited to your material.

AI image generation · online tool and model guide Krea 2 Turbo image generation · online tool and model guide ChordEdit image editing · online tool and model guide