Update README.md

README.md

@@ -1,198 +1,197 @@
 ---
 library_name: diffusers
+pipeline_tag: text-to-image
+tags:
+  - text-to-image
+  - image-generation
+  - flux
+  - dc-gen
+  - diffusers
+base_model:
+  - dc-ai/dc_flux_2K4K
+  - black-forest-labs/FLUX.1-Krea-dev
 ---
 
-# Model Card for Model ID
+# blanchon/dc_flux_krea_diffusers
 
-<!-- Provide a quick summary of what the model is/does. -->
+**Diffusers-compatible port of DC-Gen-FLUX (Krea)** for efficient high-resolution text-to-image generation (2K / 4K).
 
+This repository repackages the original **DC-Gen FLUX.1-Krea checkpoint** into a 🧨 **Diffusers** `DiffusionPipeline`, enabling standard Diffusers workflows while preserving the behavior and performance of the upstream model.
 
+---
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+**FLUX.1 DC-Gen Krea [dev]** is a DC-Gen–adapted FLUX.1-Krea checkpoint that replaces the original FLUX VAE with a **deeply compressed DC-AE latent space**.  
+Using **embedding alignment** followed by **lightweight LoRA fine-tuning**, DC-Gen enables much faster native **2K / 4K image generation** while preserving the base model’s realism and text-rendering quality.
 
-This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
+This repository does **not** retrain the model. It only provides a **Diffusers port** of the upstream checkpoint for easier inference and deployment.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **DC-Gen method & model:** NVIDIA DC-Gen team  
+  (Wenkun He*, Yuchao Gu*, Junyu Chen*, Dongyun Zou, Yujun Lin, Zhekai Zhang, Haocheng Xi, Muyang Li, Ligeng Zhu, Jincheng Yu, Junsong Chen, Enze Xie, Song Han, Han Cai)
+- **Diffusers port:** @blanchon
+- **Model type:** Text-to-image diffusion (FLUX family, rectified flow transformer)
+- **License:** FLUX.1 [dev] **Non-Commercial License** (same as upstream)
+- **Upstream checkpoint:** `dc-ai/dc_flux_2K4K`
+- **Base model family:** `black-forest-labs/FLUX.1-Krea-dev`
 
-### Model Sources [optional]
+---
 
-<!-- Provide the basic links for the model. -->
+## Model Sources
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **DC-Gen project:** https://github.com/dc-ai-projects/DC-Gen  
+- **DC-Gen homepage:** https://hanlab.mit.edu/projects/dc-gen  
+- **Paper:** https://arxiv.org/abs/2509.25180  
+- **Upstream checkpoint:** https://huggingface.co/dc-ai/dc_flux_2K4K  
+- **FLUX.1-Krea base model:** https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev  
 
-## Uses
+---
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+## Uses
 
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
+- High-resolution text-to-image generation (1024 → 4096 px)
+- Diffusers-based inference, demos, and deployment
+- Research on efficient latent-space diffusion and high-resolution synthesis
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+### Downstream Use
 
-[More Information Needed]
+- Further research or finetuning **only if compliant with the upstream license**
+- Integration into non-commercial creative or research tools
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+- Commercial usage (not permitted by the FLUX.1-dev license)
+- Illegal, harmful, or deceptive content generation
 
-[More Information Needed]
+---
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+- The model may reproduce societal biases present in its training data.
+- High-resolution generation is GPU- and VRAM-intensive.
+- Outputs are not guaranteed to be factual or safe without moderation.
+- This repo does not introduce new safety mechanisms beyond those of the base model.
 
 ### Recommendations
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+- Review the FLUX.1-dev non-commercial license carefully before use.
+- Apply standard content filtering and safety practices in downstream applications.
+- Expect memory usage to scale significantly with resolution.
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+---
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+### Minimal Load
 
-[More Information Needed]
+```python
+import torch
+from diffusers import DiffusionPipeline
 
-## Training Details
-
-### Training Data
+pipe = DiffusionPipeline.from_pretrained(
+    "blanchon/dc_flux_krea_diffusers",
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16,
+).to("cuda")
+````
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+### Image Generation Example
 
-[More Information Needed]
+```python
+import torch
+from diffusers import DiffusionPipeline
 
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
+pipe = DiffusionPipeline.from_pretrained(
+    "blanchon/dc_flux_krea_diffusers",
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16,
+).to("cuda")
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+prompt = "a tiny astronaut hatching from an egg on mars"
 
-### Testing Data, Factors & Metrics
+image = pipe(
+    prompt=prompt,
+    width=2048,
+    height=2048,
+    guidance_scale=4.5,
+    num_inference_steps=28,
+    output_type="pil",
+).images[0]
 
-#### Testing Data
+image.save("dc_flux_krea.png")
+```
 
-<!-- This should link to a Dataset Card if possible. -->
+For reproducible results, pass a seeded `torch.Generator(device="cuda")`.
 
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
+---
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+## Training Details
 
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+### Training Data
 
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+This repository does **not** introduce new training data.
 
-## Technical Specifications [optional]
+According to the DC-Gen paper, post-training uses **synthetic data generated from the base model** to adapt it to a deeply compressed latent space.
 
-### Model Architecture and Objective
+### Training Procedure
 
-[More Information Needed]
+DC-Gen applies:
 
-### Compute Infrastructure
+1. **Embedding alignment** to bridge the representation gap between latent spaces
+2. **LoRA fine-tuning** to recover base-model quality
 
-[More Information Needed]
+See the DC-Gen paper for full methodological details.
 
-#### Hardware
+---
 
-[More Information Needed]
+## Evaluation
 
-#### Software
+This repository does not add new evaluation results.
 
-[More Information Needed]
+All reported quality, throughput, and latency benchmarks originate from the DC-Gen technical report.
 
-## Citation [optional]
+---
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+## Technical Specifications
 
-**BibTeX:**
+### Architecture
 
-[More Information Needed]
+* FLUX-family text-to-image diffusion model
+* Rectified flow transformer
+* Deeply compressed DC-AE latent space (DC-Gen)
 
-**APA:**
+### Hardware Requirements
 
-[More Information Needed]
+* CUDA-capable GPU strongly recommended
+* 2K/4K generation requires substantial VRAM (≥24 GB recommended)
 
-## Glossary [optional]
+---
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+## Citation
 
-[More Information Needed]
+If you use this model in research, please cite:
 
-## More Information [optional]
+```bibtex
+@article{he2025dc,
+  title={DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space},
+  author={He, Wenkun and Gu, Yuchao and Chen, Junyu and Zou, Dongyun and Lin, Yujun and Zhang, Zhekai and Xi, Haocheng and Li, Muyang and Zhu, Ligeng and Yu, Jincheng and others},
+  journal={arXiv preprint arXiv:2509.25180},
+  year={2025}
+}
+```
 
-[More Information Needed]
+---
 
-## Model Card Authors [optional]
+## Model Card Authors
 
-[More Information Needed]
+* **DC-Gen research & model:** DC-Gen team (NVIDIA)
+* **Diffusers port & model card:** @blanchon
 
 ## Model Card Contact
 
-[More Information Needed]
+* For research questions: see the DC-Gen project page
+* For Diffusers port issues: use the Hugging Face Discussions tab