Dezgo SD / Flux playground, 2× upscale

Dezgo (dezgo.com) is a Stable Diffusion / Flux playground with a matching developer API — not DeepAI’s named HD / Genius / Super Genius 2K modes, and not Deep Dream Generator’s 2015 community of 30+ hosted models. Public text-to-image SD1 app: pick a checkpoint, write a prompt and an optional negative prompt, set guidance, steps, sampler and seed. Upscale is listed as Real-ESRGAN, factor 2 only. They also ship Flux 1 and Flux 2 apps (Flux 2 lists an aspect-ratio control). The API (dev.dezgo.com) lists SD 1/2, SDXL (total pixels capped at 1,048,576, so 1024×1024 is in range) and Flux, plus LoRA adapters. Treat 1024 / 2× as Dezgo rows, not a first-party Dezgo 4K picker of this site’s. This page is stills. ImgToVid does not run Dezgo; the generator on this page drafts on GPT Image 2.5 Flare.

01 — Capabilities

An SD/Flux steps desk, not Genius 2K modes or a 30-model community

Public Dezgo pages sell a checkpoint plus steps and a sampler. They do not sell DeepAI’s Super Genius 2K still, or DDG’s hosted-model picker.

01
A prompt + checkpoint + steps → a PNG still on dezgo.com
That file stays on Dezgo.
02
SDXL listed at 1024 / 1MP; Real-ESRGAN upscale listed as 2× only
This page does not open that studio.
03
Image-to-image / inpainting listed; LoRAs on the API — not a 14-ref picker here
Not this site’s Dezgo generate table.
04
Not DeepAI’s Genius / Super Genius 2K, not DDG’s 30+ hosted models + DeepStyle
DeepAI is a named-mode desk. DDG is the community picker. Dezgo is the SD playground. This site does not open Dezgo.

02 — Prompt to output

Prompts that match the stills above

Each prompt describes the picture on its card. “Use this prompt” sends that text to Create. The generator on this page runs GPT Image 2.5 Flare, not Dezgo.

01 · Portrait
PromptClose photographic portrait of a young man with curly hair wearing a grey knit sweater, soft window light, he glances aside and smiles warmly, shallow depth of field.
02 · Product
PromptA clean white leather sneaker on a pale grey seamless studio backdrop, soft diffused light, three-quarter view, crisp stitching, minimal commercial photograph.
03 · Street
PromptPhotographic view down a cobblestone lane in an old European village, climbing roses on stone walls, café tables in morning sun, a few people strolling in the distance.
04 · Character
PromptPhotograph of a young woman with shoulder-length brown hair in an olive t-shirt, golden late-afternoon light, she turns her head and looks into the distance, breeze in her hair.

03 — Where it fits

Jobs an SD playground is selling

Public pages point at a checkpoint, steps and a seed. They do not sell a DeepAI Super Genius still, or a DDG DeepStyle pair.

One SD or Flux still with steps, sampler and seed
That job is Dezgo’s generate table. This page does not open that job.
2× Real-ESRGAN, or an SDXL 1024 / 1MP API still
Delivery stays on Dezgo.
DeepAI Genius 1024 / Super Genius 2K, or a DDG 30-model pick
That is DeepAI or Deep Dream Generator. Dezgo is the SD playground.
A draft still on ImgToVid
Write the still here. GPT Image 2.5 Flare carries the prompt into Create. Membership and credits are checked there.

04 — Verdict

What Dezgo actually is

Strengths

dezgo.com: SD1 / Flux apps with steps, sampler, seed, negative prompt
Real-ESRGAN upscale listed as factor 2 only
API lists SDXL at 1024 / 1MP cap, plus LoRA adapters
Honest that 2× / 1024 are Dezgo rows, not a 4K Nano Banana picker here

Trade-offs

No first-party Dezgo 4K generate picker here — upscale is listed as 2× Real-ESRGAN
A Dezgo job on dezgo.com is not this site’s generate table
Dezgo is not available on ImgToVid
Marked coming soon on this site

05 — Side by side

Dezgo, Nano Banana 2 and GPT Image 2.5

Dezgo is an SD/Flux playground. Nano Banana 2 and GPT Image 2.5 numbers below are from those vendors’ public docs on ImgToVid. A 1024 SDXL still there is not a Dezgo generate row here.

	Dezgo	Nano Banana 2	GPT Image 2.5
Developer	Dezgo	Google	OpenAI
Top resolution	SDXL listed 1024 / 1MP; upscale 2×	4K	4K
Reference images	Optional image-to-image / inpainting	Up to 14	Up to 16
Images per run	1	1	1
Extreme frames	Flux 2 lists aspect; not a 1:8 / 8:1 picker here	1:8 and 8:1	1:3 and 3:1
On ImgToVid	Coming soon	Available now	Available now

06 — How it works

Start a still on ImgToVid

Step 1
Describe one still
Subject, light, frame. Dezgo will not be the model that runs it.
Step 2
Use the generator on this page
It runs GPT Image 2.5 Flare, because Dezgo is not offered here. The prompt and the settings carry into Create.
Step 3
Generate in Create
Membership and credits are checked there. Coming back to this page does not switch the model over to Dezgo.

07 — FAQ

Dezgo, in plain terms

What is Dezgo?

Dezgo is a Stable Diffusion / Flux playground on dezgo.com, with a developer API at dev.dezgo.com. ImgToVid does not host Dezgo.

What resolution does Dezgo output?

SDXL is listed at 1024 with a 1MP pixel cap. The web upscale is Real-ESRGAN, factor 2 only. That is not a Dezgo 4K picker here.

Does Dezgo generate images from text?

Yes — a prompt, a checkpoint, steps and a sampler. That is dezgo.com, not a one-shot still on ImgToVid.

How many images per run?

The public apps return one still. A Count control is listed under Power Mode. This site does not open that desk.

Can I generate Dezgo images on ImgToVid?

No. The generator on this page runs GPT Image 2.5 Flare so you can draft a still. Dezgo is marked coming soon.

Can I use the results commercially?

Commercial use of anything you generate on ImgToVid depends on your plan. Check Pricing and our Terms before you publish, and make sure prompts and uploads do not infringe someone else’s rights.