Instructions to use honghong3/VER9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use honghong3/VER9 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("honghong3/VER9", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
|
Download README.md from honghong3/VER9: direct link, hf CLI and curl.
- Browser
- Download file 6.35 kB
-
https://huggingface.co/honghong3/VER9/resolve/main/README.md
- Command line
-
hf download hf://honghong3/VER9/README.md
-
curl -L -o README.md https://huggingface.co/honghong3/VER9/resolve/main/README.md
6.35 kB
metadata
license: mit
library_name: diffusers
pipeline_tag: text-to-image
tags:
- mmdit
- text-to-image
- flow-matching
- dc-ae
- t5
language:
- en
- ko
Diffusion MMDiT Text2img with DC-AE f32c32
Update β 2026.11.20 Sampling: ETA injection equation selection & per-step latent β frame save
ETA mode
eta_mode = cos | ln
ln: eta * ln(2 / (1 + x)) / ln 2
Code: src.utilities.predict
Eta: 0 is deterministic. The larger it is, the more fresh noise is injected at each step.Eta mode: schedule of the injected noise over the steps. Selectable in all three tabs.
Frame save
Collect the latent at every step, decode all of them into images, and save them as an MP4.
Toggle with Frame save in the Sampling panel.
Batch
Generate 1β8 images at once. When Batch is greater than 1, numbered buttons under the result switch between images. Hover over an image to see its seed.
Detailing & Inpainting
Both tabs share the same mask painter with two layers.
| Color | Mode | Meaning |
|---|---|---|
| Red | μ¬μμ± (Regen) | Area to redraw |
| Blue | 보쑴 (Keep) | Area that never changes |
| β | μ§μ°κ° (Erase) | Remove paint from both layers |
- Painting one color erases the other under the brush. The later stroke wins, so the layers never overlap.
- If nothing is painted, the whole image (inpainting) or the whole crop (detailer) is redrawn.
- Keep overrides Regen. The final redraw area is
regen Γ (1 β keep). - Masks are resized to the sampling resolution with nearest-neighbor, so they stay binary.
- Start T (0β1): the point in the schedule where redrawing starts. Higher values change more, lower values stay closer to the original. For a full redraw without a mask, around 0.6 is recommended.
- Brush: brush size in px.
Inpainting
- Enter the image path and press Load.
- Paint the Regen / Keep areas on the Original panel.
- Press Generate. The result appears on the right and is saved to
inpainting/.
The image is fitted so that the long side is 1024 and the short side is snapped to a multiple of patch_size Γ compression_ratio.
Detailer
- Enter the image path and press Load.
- Drag a rectangle on the Original panel. The rectangle snaps to multiples of
patch_size Γ compression_ratio, and only sizes that scale cleanly toallowable_sizeon the long side are allowed. - The selected area appears enlarged in Crop Β· Mask. Paint the Regen / Keep areas there. The label under the crop shows the original size β the enlarged size.
- Press Generate. The crop is redrawn at the enlarged size, scaled back down, and pasted into the original image. The result is saved to
detailer/.
UI
- Three tabs: Text2img, Inpainting, Detailer. The last tab is remembered, and
#txt2img,#inpainting,#detailerin the URL open that tab directly. - Tag Browser: browse and search tags by type, and click to add them to the prompt.
- Tags autocomplete and History: click a history entry to restore the input plus the expanded tags.
- κ³ μ (Fixed) switch: when on, only the entered tags are used and no LLM tag expansion happens.
- Only one job runs at a time. Generation runs in a background thread and the browser polls for the result, so long jobs do not hit proxy timeouts.
Installation
python -m pip install -r requirements.txt
Architecture
- Autoencoder: DC-AE f32c32 (32Γ compression, 32 latent channels)
- Text Encoder: T5-Large
- Backbone: MMDiT with Joint Attention
- Implementation: Custom implementation (no pretrained base model)
- Parameters: 4B
Train Environment
- Framework: PyTorch (no custom CUDA kernels)
- GPU: NVIDIA RTX PRO 6000 (96GB VRAM)
- Platform: Google Colab
Training
Configuration
- Batch Size: Micro-batch 4 Γ Gradient Accumulation 8 = Effective Batch 32
- Training Speed: ~2.3 s / optimizer step
- Max Resolution: 1024 Γ 1024
- Dataset: 2M images
- Objective: Flow Matching (shift = 3.0)
- Precision: BF16
- Optimizer: AdamW
- Learning Rate: 1e-4
- EMA: Enabled
Training Stages
| Stage | Description | Steps | Patch Size |
|---|---|---|---|
| Stage 1 | Pre-training | 600K | 2 |
| Stage 2 | Fine-tuning | 11K | 1 |
Stage 2 Notes:
- Reset patch embedding weights.
- Reset output projection weights.
Loss by Noise Level
| Noise Level | Average Loss |
|---|---|
| 1.0 β 0.9 | 4.0 ~ 4.3 |
| 0.9 β 0.8 | 2.9 ~ 3.1 |
| 0.8 β 0.7 | 2.4 ~ 2.6 |
| 0.7 β 0.6 | 2.0 ~ 2.1 |
| 0.6 β 0.5 | 1.8 ~ 1.9 |
| 0.5 β 0.4 | 1.6 ~ 1.7 |
| 0.4 β 0.3 | 1.3 ~ 1.6 |
| 0.3 β 0.2 | 1.2 ~ 1.4 |
| 0.2 β 0.1 | 1.0 ~ 1.1 |
Generation Results
Patch Size 2 + DC-AE f32c32
- Issue: Facial features, particularly the eyes, tend to collapse or become distorted.
- Observation: Limited spatial detail makes accurate reconstruction of fine facial features challenging.
Patch Size 1 + DC-AE f32c32
- Fine-tuning Result: Fine-tuning with patch size 1 improved facial feature reconstruction.
- Improvement: Eye and facial distortions were partially resolved, with better preservation of fine details.
Current Limitations
- Full-body Generation: Full-body generation remains challenging due to insufficient full-body samples in the training dataset.
- Observation: The current dataset contains insufficient full-body examples to learn consistent full-body composition and anatomical details.
- Future Work: Increase the proportion and diversity of full-body images in the training dataset.
Train Architecture
- Use Cache
- Cpu Multi Threading
Inference Architecture
UI
- Sampling
- Inpainting
- Result







