vs

192 evaluations across 6 categories

Benchmark V1 verdicts are produced by VLM judges and can contain mistakes. Treat PASS/FAIL labels as machine-assisted assessments, and inspect the images yourself. Learn more about the methodology.

Generation Details

Source-backed model context, size, cost, and request settings for this ImageBench V1 run.

local/boogu-image-turbo

Local

Boogu-Image-0.1-Turbo is Boogu's 10B Apache-2.0 open-source text-to-image turbo model, a four-step distilled variant focused on fast 1K generation, photorealism, prompt adherence, and Chinese-English text rendering.

Maker: Boogu
Family: Boogu-Image-0.1
Model Size: 10B
high
Cost: local run; no API price
not_applicable
Run Target: gx10/boogu-image-turbo
Effective Request: response_format: b64_json · size: 1024x1024 · num_inference_steps: 4
Sources: Boogu-Image-0.1-Turbo model card Boogu-Image-0.1 ComfyUI workflow

fal/reve/2.1

API

Reve 2.1 is Reve AI's flagship text-to-image model, generating natively at 4K (4096x4096) with layout intelligence — it reasons about structure and spatial hierarchy before generating. It is a standout at in-image typography (including foreign scripts) and ranks #2 on the Text-to-Image Arena, well suited to posters, packaging, and marketing design. The older fal-ai/reve/text-to-image endpoint serves the earlier Reve Image 1.0.

Maker: Reve AI
Family: Reve Image 2.1
Model Size: not disclosed
unknown
Cost: /bin/bash.04 / image
high
Run Target: fal/reve/2.1/text-to-image
Effective Request: aspect_ratio: 1:1 · seed: 7
Sources: Reve 2.1 (Text to Image) API on fal Reve 2.1 — Native 4K Image Generation with Layout Intelligence (fal)