Model card: add 8-steps-dmd2-lora, refresh cats and PartiPrompts (Kromoss rows at update 11000)

README.md

@@ -17,12 +17,14 @@ Kromoss is a full fine-tune of [MOSS-Image-Base](https://huggingface.co/OpenMOSS
 decoder) as [MOSS-Image-SFT](https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT), and this repo has the same
 layout, so it is a drop-in replacement.
 
-The repo also ships `8-steps-dmd-lora.safetensors`, an 8-step turbo LoRA (data-space DMD distillation of
-MOSS-Image-Base): **8 steps, CFG 1**, no negative branch.
+The repo also ships two 8-step turbo LoRAs distilled from MOSS-Image-Base: **8 steps, CFG 1**, no negative branch.
+- `8-steps-dmd2-lora.safetensors` (recommended): the DMD LoRA below, further trained with DMD2's GAN stage against
+  real images. Slightly more contrast and detail, and the best PartiPrompts score.
+- `8-steps-dmd-lora.safetensors`: data-space DMD distillation.
 
-| 50 steps, CFG 3 | 8 steps, CFG 1 + `8-steps-dmd-lora` |
-| --- | --- |
-| ![50 steps](assets/cat-50steps-cfg3.webp) | ![8 steps + LoRA](assets/cat-8steps-lora.webp) |
+| 50 steps, CFG 3 | 8 steps, CFG 1 + `8-steps-dmd-lora` | 8 steps, CFG 1 + `8-steps-dmd2-lora` |
+| --- | --- | --- |
+| ![50 steps](assets/cat-50steps-cfg3.webp) | ![8 steps + DMD LoRA](assets/cat-8steps-lora.webp) | ![8 steps + DMD2 LoRA](assets/cat-8steps-lora-dmd2.webp) |
 
 Checkpoint: update 11000 of the fine-tune (EMA weights), 704k training images.
 
@@ -70,11 +72,12 @@ Native ComfyUI support for MOSS-Image is in current ComfyUI master. The single f
 | `diffusion_models/kromoss_int8_convrot.safetensors` | `models/diffusion_models/` | Load Diffusion Model (int8, 5.4 GB) |
 | `text_encoders/qwen3.5_9b_bf16.safetensors` | `models/text_encoders/` | Load CLIP, type `moss_image` |
 | `vae/flux2-vae_small.safetensors` | `models/vae/` | Load VAE |
+| `8-steps-dmd2-lora.safetensors` | `models/loras/` | LoraLoaderModelOnly, strength 1 |
 | `8-steps-dmd-lora.safetensors` | `models/loras/` | LoraLoaderModelOnly, strength 1 |
 
 `kromoss_bf16.safetensors` drops in for `moss_image_sft_bf16.safetensors` in the
-Comfy-Org workflows (50 steps, CFG 3). With the LoRA, use KSampler with `euler` / `simple`, 8 steps, CFG 1.
-ComfyUI maps the LoRA's separate q/k/v onto the fused `qkv` slices.
+Comfy-Org workflows (50 steps, CFG 3). With either LoRA, use KSampler with `euler` / `simple`, 8 steps, CFG 1.
+ComfyUI maps the LoRAs' separate q/k/v onto the fused `qkv` slices.
 
 `convert_to_comfy.py` converts any MOSS-Image diffusers `transformer/` folder (e.g. your own fine-tune) into this
 single-file format (needs only `torch` and `safetensors`):
@@ -90,19 +93,24 @@ On MOSS-Image-SFT's `transformer/` it reproduces Comfy-Org's `moss_image_sft_bf1
 The 168 block linears (`proj.{qkv,o,ffn_up_gate,ffn_down}`) are stored as int8 with per-row scales, after a
 256-wide regular Hadamard rotation of the input dimension. ComfyUI rebuilds the rotation at load time and applies it
 to the activations online, so no rotation matrices are stored. Each block also selects ComfyUI's int8 attention.
-It drops in for the int8 Comfy-Org file and works with the LoRA. `quantize_convrot.py` makes it from a bf16 single
+It drops in for the int8 Comfy-Org file and works with the LoRAs. `quantize_convrot.py` makes it from a bf16 single
 file; on `moss_image_sft_bf16.safetensors` it reproduces Comfy-Org's int8 file byte for byte:
 
 ```bash
 python quantize_convrot.py my_model_bf16.safetensors my_model_int8_convrot.safetensors
 ```
 
-## 8-step turbo LoRA
+## 8-step turbo LoRAs
+
+Both were distilled from MOSS-Image-Base (50 steps, CFG 3) and transfer to Kromoss:
+- `8-steps-dmd-lora.safetensors`: data-space DMD, 12000 updates.
+- `8-steps-dmd2-lora.safetensors`: that run continued for 3000 updates with DMD2's second stage, a GAN
+  discriminator on the fake score trained against real images, at a quarter of the learning rate.
 
-`8-steps-dmd-lora.safetensors`: fp32, rank 128 / alpha 128 on every block's `proj.{q,k,v,o,ffn_up_gate,ffn_down}`,
-kohya keys (`diffusion_model.<module>.lora_down.weight` / `lora_up.weight` / `alpha`). In ComfyUI, load it with
-a LoRA loader at strength 1. With diffusers, apply it unmerged. Do not merge it into the bf16 weights: the delta
-is close to bf16's rounding step.
+Both are fp32, rank 128 / alpha 128 on every block's `proj.{q,k,v,o,ffn_up_gate,ffn_down}`, with kohya keys
+(`diffusion_model.<module>.lora_down.weight` / `lora_up.weight` / `alpha`). Use one at a time. In ComfyUI, load it
+with a LoRA loader at strength 1. With diffusers, apply it unmerged. Do not merge it into the bf16 weights: the
+delta is close to bf16's rounding step. 4 steps also works.
 
 ```python
 from safetensors.torch import load_file
@@ -118,14 +126,14 @@ def apply_lora(transformer, path, strength=1.0):
             return out + (scale * (args[0].float() @ down.T) @ up.T).to(out.dtype)
         modules[name].register_forward_hook(hook)
 
-apply_lora(pipe.transformer, "8-steps-dmd-lora.safetensors")   # hf_hub_download("lodestones/Kromoss", ...)
+apply_lora(pipe.transformer, "8-steps-dmd2-lora.safetensors")   # hf_hub_download("lodestones/Kromoss", ...)
 image = pipe(prompt, height=1024, width=1024, num_inference_steps=8, guidance_scale=1.0,
              generator=torch.Generator("cpu").manual_seed(42)).images[0]
 ```
 
 ## Sampling settings
 
-| Setting | Full model | With `8-steps-dmd-lora` |
+| Setting | Full model | With either LoRA |
 | --- | --- | --- |
 | Sampler | Flow-matching Euler | Flow-matching Euler |
 | Steps | 50 | 8 |
@@ -133,14 +141,16 @@ image = pipe(prompt, height=1024, width=1024, num_inference_steps=8, guidance_sc
 | Shift | 5 | 5 |
 | Layer skipping | Negative branch, layer index 22 | none (no negative branch) |
 
-## PartiPrompts (100 prompts, CLIP ViT-L/14 score; Kromoss rows measured at update 2000)
+## PartiPrompts (100 prompts, CLIP ViT-L/14 score; Kromoss rows measured at update 11000)
 
 | Model | CLIP |
 | --- | --- |
 | MOSS-Image-Base, 50 steps, CFG 3 | 27.19 |
-| MOSS-Image-Base + LoRA, 8 steps, CFG 1 | 27.53 |
-| Kromoss, 50 steps, CFG 3 | 26.88 |
-| Kromoss + LoRA, 8 steps, CFG 1 | **27.82** |
+| MOSS-Image-Base + `8-steps-dmd-lora`, 8 steps, CFG 1 | 27.53 |
+| MOSS-Image-Base + `8-steps-dmd2-lora`, 8 steps, CFG 1 | 27.59 |
+| Kromoss, 50 steps, CFG 3 | 27.90 |
+| Kromoss + `8-steps-dmd-lora`, 8 steps, CFG 1 | 27.99 |
+| Kromoss + `8-steps-dmd2-lora`, 8 steps, CFG 1 | **28.13** |
 
 Columns in the sheet below follow the table's order.