---
title: ImageGen – AI Image Studio
emoji: 🖼
colorFrom: purple
colorTo: red
sdk: gradio
app_file: app.py
python_version: 3.12
short_description: Multi-model AI image studio with the latest open models
pinned: true
models:
# This Space supports a wide variety of image generation pipelines. To maintain transparency, credit the original creators, and help users explore the Hugging Face ecosystem, we list and link several types of models in our metadata:
# 1. **Directly Run Models:** Models and checkpoints actively loaded by our pipelines (configured via `yaml/file_list.yaml`).
# 2. **Upstream Base Models:** The original foundation architectures from which our optimized ports, quantized versions, or wrappers are derived.
  # Directly Run Models
  - abenzerps/Qwen-Image-2.1-Uncensored-GGUF
  - AiAF/Illustrious-XL-v0.1.safetensors
  - alibaba-pai/Qwen-Image-2.1-Fun-Controlnet-Union
  - alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union-2.1
  - black-forest-labs/FLUX.1-Redux-dev
  - black-forest-labs/FLUX.2-dev-NVFP4
  - black-forest-labs/FLUX.2-klein-4b-nvfp4
  - black-forest-labs/FLUX.2-klein-9b-nvfp4
  - black-forest-labs/FLUX.2-klein-9b-kv-fp8
  - black-forest-labs/FLUX.2-klein-base-4b-nvfp4
  - black-forest-labs/FLUX.2-klein-base-9b-nvfp4
  - black-forest-labs/flux-3-image-klein-comfy
  - bluepen5805/4nima_pencil-XL
  - bluepen5805/anima-models
  - bluepen5805/anima_pencil-XL
  - bluepen5805/blue_pencil-XL
  - bluepen5805/illustrious_pencil-XL
  - bluepen5805/mellow_pencil-XL
  - bluepen5805/noob_v_pencil-XL
  - bluepen5805/pony_pencil-XL
  - cagliostrolab/animagine-xl-3.1
  - cagliostrolab/animagine-xl-4.0
  - ChenkinNoob/ChenkinNoob-XL-V0.5
  - circlestone-labs/Anima
  - Clybius/Chroma-fp8-scaled
  - comfyanonymous/ControlNet-v1-1_fp16_safetensors
  - comfyanonymous/cosmos_1.0_text_encoder_and_VAE_ComfyUI
  - comfyanonymous/flux_text_encoders
  - Comfy-Org/Anima-LLLite
  - Comfy-Org/Boogu-Image
  - Comfy-Org/ERNIE-Image
  - Comfy-Org/Fibo-2.0
  - Comfy-Org/FLUX.1-Krea-dev_ComfyUI
  - Comfy-Org/flux2-dev
  - Comfy-Org/HiDream-I1_ComfyUI
  - Comfy-Org/HiDream-O1-Image
  - Comfy-Org/HunyuanImage_2.1_ComfyUI
  - Comfy-Org/Ideogram-4
  - Comfy-Org/Krea-2
  - Comfy-Org/Lens
  - Comfy-Org/LongCat-Image
  - Comfy-Org/Lumina_Image_2.0_Repackaged
  - Comfy-Org/Mage-Flow
  - Comfy-Org/Ming-Image
  - Comfy-Org/MOSS-Image
  - Comfy-Org/NewBie-image-Exp0.1_repackaged
  - Comfy-Org/Omnigen2_ComfyUI_repackaged
  - Comfy-Org/Ovis-Image
  - Comfy-Org/PixelDiT
  - Comfy-Org/Qwen3.8-27B
  - Comfy-Org/Qwen-Image_ComfyUI
  - Comfy-Org/Qwen-Image-2.1
  - Comfy-Org/Qwen-Image-Edit_ComfyUI
  - Comfy-Org/sigclip_vision_384
  - Comfy-Org/stable-diffusion-3.5-fp8
  - Comfy-Org/vae-text-encorder-for-flux-klein-4b
  - Comfy-Org/vae-text-encorder-for-flux-klein-9b
  - Comfy-Org/Wan_2.1_ComfyUI_repackaged
  - Comfy-Org/z_image
  - Comfy-Org/z_image_turbo
  - conradlocke/krea2-identity-edit
  - cyberdelia/CyberRealisticPony
  - diffusionmodels1254ani/hassakuAnima
  - diffusionmodels1254ani/waiANIMA
  - duongve/AnimaYume
  - Eugeoter/noob-sdxl-controlnet-canny
  - Eugeoter/noob-sdxl-controlnet-depth
  - Eugeoter/noob-sdxl-controlnet-lineart_anime
  - Eugeoter/noob-sdxl-controlnet-lineart_realistic
  - Eugeoter/noob-sdxl-controlnet-manga_line
  - Eugeoter/noob-sdxl-controlnet-normal
  - Eugeoter/noob-sdxl-controlnet-softedge_hed
  - Eugeoter/noob-sdxl-controlnet-tile
  - fal/AuraFlow-v0.3
  - frankjoshua/novaAnimeXL_ilV180
  - funnycat1/Nova-Anime-AM-v4.0
  - funnycat1/Nova-Cross-AM-v1.0-C
  - funnycat1/Nova-Reality-AM-v1.0
  - funnycat1/RAMTHRUST-NSFW-PINK-ALCHEMY-ANIMA
  - Gazingstars123/Anima-2.9B
  - h94/IP-Adapter
  - h94/IP-Adapter-FaceID
  - InstantX/FLUX.1-dev-IP-Adapter
  - InstantX/Qwen-Image-ControlNet-Inpainting
  - InstantX/Qwen-Image-ControlNet-Union
  - InstantX/SD3.5-Large-IP-Adapter
  - jdopensource/JoyAI-Image-Edit-ComfyUI
  - jdopensource/JoyAI-Image-Edit-Plus-ComfyUI
  - kandinskylab/Kandinsky-5.0-T2I-Lite
  - Kijai/flux-fp8
  - Laxhar/noob_openpose
  - Laxhar/noobai-XL-1.1
  - Laxhar/noobai-XL-Vpred-1.0
  - licyk/sd_control_collection
  - lightx2v/Qwen-Image-2512-Lightning
  - lightx2v/Qwen-Image-Edit-2511-Lightning
  - LyliaEngine/Pony_Diffusion_V6_XL
  - lylogummy/Anima-3.8B
  - MIC-Lab/illustriousXLv0.1_controlnet
  - MIC-Lab/illustriousXLv1.1_controlnet
  - misri/hassakuXLIllustrious_v30
  - motimalu/kirazuri-anima
  - Noctaluna/Anima-Noct-Anime-Mix
  - Noctaluna/Krea2-Noct-Uncensored
  - Noctaluna/Noct-Q-Anime-Uncensored-Qwen-Image-2.1
  - Noctaluna/Noct-Q-Uncensored-Qwen-Image-2.1
  - nvidia/Cosmos-Predict2-2B-Text2Image
  - nvidia/Cosmos-Predict2-14B-Text2Image
  - OnomaAIResearch/Illustrious-XL-v1.0
  - OnomaAIResearch/Illustrious-XL-v1.1
  - OnomaAIResearch/Illustrious-XL-v2.0
  - ostris/krea2_turbo_style_reference
  - Patil/Krea-2-depth-controlnet
  - RedRayz/hikari_noob_v-pred_1.2.4
  - Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0
  - silveroxides/Chroma1-Radiance-fp8-scaled
  - stabilityai/sdxl-turbo
  - stabilityai/stable-diffusion-3.5-controlnets
  - stabilityai/stable-diffusion-xl-base-1.0
  - stable-diffusion-v1-5/stable-diffusion-v1-5
  - t8star/SenseNova-U1.5-Comfy
  - tori29umai/krea2-controlnet
  - tsukiyomi/krea2_raw-nvfp4
  - Wenaka/NoobAI_XL_Inpainting_ControlNet_Full
  - xinsir/anime-painter
  - xinsir/controlnet-canny-sdxl-1.0
  - xinsir/controlnet-depth-sdxl-1.0
  - xinsir/controlnet-openpose-sdxl-1.0
  - xinsir/controlnet-scribble-sdxl-1.0
  - xinsir/controlnet-tile-sdxl-1.0
  - xinsir/controlnet-union-sdxl-1.0
  - XLabs-AI/flux-controlnet-collections
  - zhenshipo/waiIllustriousSDXL_v170
  # Upstream Base Models
  - AIDC-AI/Ovis-Image-7B
  - Alpha-VLLM/Lumina-Image-2.0
  - alibaba-pai/Qwen-Image-2.1-Fun-Controlnet-Union
  - baidu/ERNIE-Image
  - baidu/ERNIE-Image-Turbo
  - black-forest-labs/FLUX.1-dev
  - black-forest-labs/FLUX.1-Krea-dev
  - black-forest-labs/FLUX.1-schnell
  - black-forest-labs/flux-3-image-klein
  - black-forest-labs/flux-3-image-klein-base
  - black-forest-labs/flux-3-image-klein-pup
  - Boogu/Boogu-Image-0.1-Turbo
  - Boogu/Boogu-Image-0.1-Base
  - Boogu/Boogu-Image-0.1-Edit
  - Boogu/Boogu-Image-0.1-Edit-Turbo
  - briaai/Fibo-2.0-dev
  - briaai/Fibo-2.0-edit-turbo
  - chinoll/Moss-Image-Edit
  - darask0/MOSS-Image-color-depth-control
  - HiDream-ai/HiDream-I1-Dev
  - HiDream-ai/HiDream-I1-Fast
  - HiDream-ai/HiDream-I1-Full
  - HiDream-ai/HiDream-O1-Image
  - HiDream-ai/HiDream-O1-Image-Dev
  - ideogram-ai/ideogram-4-fp8
  - inclusionAI/Ming-Image-0.1-Design
  - kohya-ss/Anima-LLLite
  - krea/Krea-2-Raw
  - krea/Krea-2-Turbo
  - lodestones/Chroma1-HD
  - lodestones/Chroma1-Radiance
  - mage-flow-community/Mage-Flow
  - mage-flow-community/Mage-Flow-Base
  - mage-flow-community/Mage-Flow-Edit
  - mage-flow-community/Mage-Flow-Edit-Base
  - mage-flow-community/Mage-Flow-Edit-Turbo
  - mage-flow-community/Mage-Flow-Turbo
  - meituan-longcat/LongCat-Image
  - microsoft/Lens
  - microsoft/Lens-Turbo
  - NewBie-AI/NewBie-image-Exp0.1
  - nvidia/PiD
  - nvidia/PixelDiT-1300M-1024px
  - OmniGen2/OmniGen2
  - OpenMOSS-Team/MOSS-Image-Base
  - OpenMOSS-Team/MOSS-Image-SFT
  - Qwen/Qwen3.8-27B
  - Qwen/Qwen-Image
  - Qwen/Qwen-Image-2512
  - Qwen/Qwen-Image-2.1
  - Qwen/Qwen-Image-2.1-Turbo
  - Qwen/Qwen-Image-2.1-PE-I2I
  - Qwen/Qwen-Image-2.1-PE-T2I
  - Qwen/Qwen-Image-Edit
  - Qwen/Qwen-Image-Edit-2509
  - Qwen/Qwen-Image-Edit-2511
  - sensenova/SenseNova-U1.5-8B-MoT
  - sensenova/SenseNova-U1.5-8B-MoT-SFT
  - stabilityai/stable-diffusion-3.5-large
  - stabilityai/stable-diffusion-3.5-medium
  - tencent/HunyuanImage-2.1
  - Tongyi-MAI/Z-Image
  - Tongyi-MAI/Z-Image-Turbo
---

# ImageGen — AI Image Studio

**ImageGen** is a multi-model image generation Space built to make experimenting with modern image-generation workflows easier from one interface.

Explore different image models and workflows, compare results, and create images without setting up a local environment.

<p align="center">
  <a href="https://huggingface.co/spaces/ItNero/ImageGen-32">
    <strong>🚀 Open ImageGen and try it</strong>
  </a>
</p>

## What you can explore

- **Multiple model families** — an evolving selection of image-generation models and pipelines.
- **Anime and illustration** — explore anime-focused checkpoints and illustration workflows where available.
- **General image generation** — experiment with supported models for a range of visual styles.
- **Flexible workflows** — the project is designed around multi-task, dynamically configured, chainable workflows.
- **ComfyUI ecosystem** — integrations and model pipelines are part of the project.

> Available models, options, and workflows may change as the Space is updated. The controls shown in the live app are the source of truth for current availability.

## How to use

1. Open the [ImageGen Space](https://huggingface.co/spaces/ItNero/ImageGen-32).
2. Wait for the Space and its required model components to finish loading.
3. Choose an available workflow or model in the interface.
4. Enter your prompt and adjust the options exposed by that workflow.
5. Generate your image and save the result if the interface provides that option.

## Tips for better results

- Be clear about the subject, action, setting, and composition.
- Use model-appropriate prompts; different model families may interpret the same prompt differently.
- Start with the default settings, then change one setting at a time.
- If a workflow is loading or unavailable, try again later; large model downloads and shared compute can affect startup time.

## Models and credits

ImageGen brings together model integrations from the Hugging Face ecosystem. The original model authors retain ownership of their work.

Please visit each model's Hugging Face page and read its model card and license before using its outputs, especially for commercial use. Model availability and usage rights depend on the individual model and its license.

This Space is based on [RioShiina/ImageGen](https://huggingface.co/spaces/RioShiina/ImageGen) and is distributed under the same license terms.

## Community and feedback

Found a bug, a loading issue, or a workflow that could be improved? Share a clear description of the issue, the selected workflow/model, and (if possible) the error message.

If you share results made with ImageGen, consider including the model and prompt settings so others can learn from your workflow.

## Important notes

- This Space is provided as-is; generation speed and availability depend on the selected model and available compute.
- Generated images, prompts and settings are saved for research and model-training purposes.
- Do not upload private, confidential, or sensitive material.
- Only create and share content that you have the right to use and that complies with applicable laws and the relevant model's license and usage rules.

---

<p align="center">
  Made for experimenting, creating, and exploring AI image workflows.
  <br />
  <a href="https://huggingface.co/spaces/ItNero/ImageGen-32">Launch ImageGen →</a>
</p>