Try Kling Image V4 Long for Page Mockups from Kling AI →
Models
Agents
Workflows
Studio
PricingBlogDocs
ExploreDiscover models by categoryDiscoverModels and effects built by WiroBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
Generative Media AgentCreate and edit media by chattingWorkflow AgentBuild visual workflows with Agent
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick connectors and skills, choose a plan, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building
Explore models/
Image GenerationActive

Hunyuan Flux SRPO

bytencent

Hunyuan Flux SRPO is FLUX.1 dev (12B) fine-tuned by Tencent Hunyuan with SRPO, a human-preference training method aimed at realism and aesthetic quality without oversaturated color.

Text to ImageFast InferenceFluxBf16
Model ID
Hunyuan-Flux-SRPO
Provider
tencent
Updated
Nov 7, 2026, 03:15
Hunyuan-Flux-SRPO
4
Comments
Average rating : 4.4 (5 users)
Providertencent
ModelHunyuan-Flux-SRPO
Text to ImageFast InferenceFluxBf16
wiro playground—tencent/Hunyuan-Flux-SRPO
0 / 1
Maximum 1 image allowed

(Optional) Provide an image file or an image URL. If you do not provide an image, the generation process will run only with the prompt.

Tell us about any details you want to generate

Your request will cost $0.0006 per second.

Running this model on Wiro costs approximately $0.039457 in total.

(Total cost varies depending on the request's execution time.)
Sample outputs
Sample 1
Sample 2
Sample 3
Sample 4
Click To See More Samples
Updated Nov 7, 2026, 03:15

Overview

Hunyuan Flux SRPO is FLUX.1 dev, the 12B-parameter flow transformer from Black Forest Labs, with its transformer weights fine-tuned by Tencent Hunyuan. Tencent published the checkpoint, paper and inference code on September 8, 2025, and the training code four days later, under the name SRPO (Semantic Relative Preference Optimization).

The method has two parts. Direct-Align uses a predefined noise prior so a clean image can be recovered from any denoising step, which lets training cover the whole diffusion trajectory and avoids over-optimizing the late steps. SRPO turns the reward into a text-conditioned signal that can be adjusted with positive and negative prompt words. This checkpoint was trained on the HPD dataset with HPSv2 as the reward. Tencent reports that the method improves the human-evaluated realism and aesthetic quality of FLUX.1 dev by over 3x, without reward hacking such as drifting toward oversaturated color.

Only the transformer changes. The text encoders and the VAE come from FLUX.1 dev, so it reads prompts the same way FLUX.1 dev does.

What you can build

  • Side-by-side realism studies against FLUX.1 dev on the same prompt and seed, looking at skin, fabric and light. The samples include a close-up of a woman in traditional Chinese dress and a full-length shot of a man on a misty street.
  • Evaluation sets for human-preference and aesthetic scoring research, across photographic and illustrated prompts such as the blue night scene of people at a bus stop.
  • Studies of how preference tuning treats painterly styles. The Ophelia sample uses the Pre-Raphaelite prompt from Tencent's own quick-start example.
  • Tests of title lettering and creature prompts, such as the Underealm cover and the furry, amber-eyed creature in the samples.

Inputs

  • Prompt: a description of the image in plain sentences. The T5 text encoder reads up to 512 tokens, while the CLIP encoder keeps only the first 77, so put the subject and style at the start of a long prompt.
  • Width and height: up to 2048 pixels each, 1024 x 1024 by default.
  • Inference steps (default 20) and guidance scale (1 to 20, default 3.5).
  • Samples: 1 to 8 images per run.
  • Seed: fix it to reproduce a result or to compare prompt edits.

Outputs

PNG images, one file per sample, at the width and height you set rounded down to a multiple of 16 pixels.

Recommended settings

  • Tencent's reference settings are guidance 3.5, 1024 x 1024 and 50 steps. The default of 20 steps is enough for trying out prompts; move toward 50 for final images where texture and small detail matter.
  • Keep guidance close to 3.5.
  • Wide frames work well. Two of the samples here were made at 1024 x 576.

Limitations

  • The fine-tune targets human-preference scores for realism and aesthetics. Prompt understanding still comes from the unchanged FLUX.1 dev text encoders.
  • Large title lettering comes out legibly, but small secondary text can be garbled, as in the line under the title on the Underealm sample.

Safety & compliance

Tencent's license terms for the SRPO weights allow academic use only and rule out commercial or production use. As a fine-tune of FLUX.1 [dev], the weights also fall under Black Forest Labs' FLUX.1 [dev] Non-Commercial License, which limits the model and its derivatives to non-commercial use, forbids using outputs to train, fine-tune or distill a model that competes with FLUX.1 [dev], and prohibits unlawful or infringing content.

Example prompts

Great starting points for Hunyuan-Flux-SRPO.

A sad-faced Russian man in white Adidas pants and a black jacket stands alone on a street in an extreme long shot digital painting.Image Generation
A close up portrait of a Chinese princess wearing colorful clothing with a highly detailed face and eyes.Image Generation
A cosmic animal portrait featuring fractal and Lovecraftian elements, done in a Pixar-inspired style by artists Eaton, Stanley, Artgerm, and Bagshaw.Image Generation
The album cover for the band Underealm features an evil entity in a sophisticated suit, with dark and intricate details.Image Generation
Several people waiting at a bus stop in a dark city night, depicted in a digital illustration.Image Generation

API quick start

Run Hunyuan-Flux-SRPO with a single API call.

POST https://api.wiro.ai/v1/Run/tencent/hunyuan-flux-srpo
{
  "prompt": "A close up portrait of a Chinese princess…",
  "inputImage": "https://your-cdn.com/input.png",
  "steps": 20,
  "scale": 3.5
}
curl
curl -X POST "https://api.wiro.ai/v1/Run/tencent/hunyuan-flux-srpo" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_WIRO_API_KEY" \
  --data-binary @- <<'JSON'
{
  "prompt": "A close up portrait of a Chinese princess…",
  "inputImage": "https://your-cdn.com/input.png",
  "steps": 20,
  "scale": 3.5
}
JSON

Other models you might like

Explore similar image generation models.

View all
HunyuanWorld-text-to-panorama
Text to Image

HunyuanWorld-text-to-panorama

tencent

text-to-image-flux-fast
Text to Image

text-to-image-flux-fast

wiro

FLUX.1-schnell
Text to Image

FLUX.1-schnell

black-forest-labs

FLUX.1-dev
Text to Image

FLUX.1-dev

black-forest-labs

  • FLUX.1-Krea-devblack-forest-labs
  • text-to-image-fluxwiro
  • FLUX.1-dev-fp8-v1.0abdallahalswa80
  • p-imagepruna
  • U1-8B-Text-to-Imagesensenova
  • Z-Image-Turbotongyi-mai
  • text-to-image-flux-lora-fastwiro
  • lensmicrosoft

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroModelsAgentsMCP ServerLLM GatewayBrowser ExtensionIntegrationsPricingAboutBlogCareersContactPartnerChangelogStatusFAQ
CategoriesText to ImageImage to ImageImage EditingImage to TextText to VideoImage to VideoVideo to VideoText to SpeechSpeech to TextSpeech to SpeechVoice CloneRealtime ConversationMusic GenerationLLMUtilities
ModelsNano Banana 2GPT Image 2.5Seedream V5 ProSeedance 2.5Veo 3.1Kling V3FLUX 3FLUX.2 ProWan 3.0 PrimeGrok Imagine 1.5
PartnersGoogleOpenAIByteDanceBlack Forest LabsKling AIQwenAlibabaxAIMiniMaxElevenLabs
Getting StartedWiro ModelsWiro EffectsIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion