Run the workflows on ComfyUI's native P-H3-Image support

44a0fb7 verified 1 day ago

17.8 kB

---
license: other
license_name: minimax-h3-community-license-agreement
license_link: LICENSE
base_model: PrunaAI/p-h3-image
base_model_relation: quantized
pipeline_tag: text-to-image
language:
- en
tags:
- comfyui
- diffusion-single-file
- text-to-image
- image-to-image
- image-generation
- image-editing
- prompt-upsampling
- lora
- int8
- 4-bit
- minimax-h3
- pruna-ai
---
<!-- header start -->
<p align="center">
  <img src="assets/p-h3-image-comfy.jpg" width="800">
</p>
<!-- header end -->

<p align="center">
  <a href="https://github.com/PrunaAI/pruna">
    <img src="https://img.shields.io/badge/GitHub-PrunaAI-9334E9?style=plastic&logo=github&logoColor=white" alt="GitHub">
  </a>
  &nbsp;
  <a href="https://twitter.com/PrunaAI">
    <img src="https://img.shields.io/badge/Twitter%2FX-@PrunaAI-9334E9?style=plastic&logo=x&logoColor=white" alt="Twitter/X">
  </a>
  &nbsp;
  <a href="https://www.linkedin.com/company/pruna-ai">
    <img src="https://img.shields.io/badge/LinkedIn-PrunaAI-9334E9?style=plastic&logo=linkedin&logoColor=white" alt="LinkedIn">
  </a>
  &nbsp;
  <a href="https://discord.com/invite/JFQmtFKCjd">
    <img src="https://img.shields.io/badge/Discord-Join%20us-9334E9?style=plastic&logo=discord&logoColor=white" alt="Discord">
  </a>
  &nbsp;
  <a href="https://dashboard.pruna.ai/login?utm_source=huggingface&utm_medium=org_card&utm_campaign=hf_traffic">
    <img src="https://img.shields.io/badge/Performance%20Models-Try%20them%20now-9334E9?style=plastic&logo=data:image/svg%2bxml;base64,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" alt="Performance Models">
  </a>
</p>
<div align="center">
<h1 style="color: #9334E9;">P-H3-Image</h1>

<h2>ComfyUI files for P-H3-Image, based on MiniMax-H3</h2>

<h3>
  <span style="color: #9334E9;">bf16, int8 and w4a8</span>
  &nbsp;·&nbsp;
  <span style="color: #9334E9;">From 21 GB of VRAM</span>
  &nbsp;·&nbsp;
  <span style="color: #9334E9;">8 steps</span>
  &nbsp;·&nbsp;
  Text-to-image and editing with up to 8 images
</h3>

</div>

This repository holds the ComfyUI files for **P-H3-Image**, an image model for text-to-image generation and image
editing based on [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3). It renders 8-megapixel images in 8 steps
without CFG and edits with up to 8 input images. Every component comes in bf16 and in ComfyUI's native int8 and 4-bit
formats. The smallest set is a 20 GB download that peaks at 21 GB of VRAM at 8 MP, against 143 GB of weights for
MiniMax-H3.

ComfyUI supports P-H3-Image natively, no custom nodes needed. The diffusers pipeline is
in [PrunaAI/P-H3-Image](https://huggingface.co/PrunaAI/P-H3-Image). Try it in the [Hugging Face Spaces](https://huggingface.co/spaces/PrunaAI/P-H3-Image). Read the full blog post [here](https://pruna.ai/blog/oss-p-h3-image-launch).

## Quickstart

1. **Update ComfyUI.** P-H3-Image support is on ComfyUI's master branch and ships with the next release. Until then,
   update to the latest ComfyUI from GitHub (nightly). The desktop app and Comfy Cloud follow stable releases and get it
   with the next one.

   ```bash
   cd ComfyUI && git pull
   ```

2. **Download one file per component** into `ComfyUI/models`. The bf16 set, a 55 GB download plus the prompt upsampler,
   peaks at about 56 GB of VRAM:

   ```bash
   hf download PrunaAI/P-H3-Image-comfy --include "diffusion_models/p-h3-image_bf16.safetensors" "text_encoders/p-h3-image_text_encoder_bf16.safetensors" "text_encoders/p-h3-image_prompt_upsampler_bf16.safetensors" "vae/p-h3-image_vae_bf16.safetensors" --local-dir ComfyUI/models
   ```

   The smallest set, a 20 GB download plus the prompt upsampler, peaks at about 21 GB of VRAM:

   ```bash
   hf download PrunaAI/P-H3-Image-Comfy --include "diffusion_models/p-h3-image_w4a8.safetensors" "text_encoders/p-h3-image_text_encoder_w4a8.safetensors" "text_encoders/p-h3-image_prompt_upsampler_bf16.safetensors" "vae/p-h3-image_vae_int8_convrot.safetensors" --local-dir ComfyUI/models
   ```

3. **Open a workflow** from `workflows/`, type a short request and run. The
   workflows render at 8 MP in 8 steps through the prompt upsampler.

## Pick your files

Pick one file per component. Files of different precisions can be mixed freely.

| Component | Folder | bf16 | int8 (`int8_convrot`) | w4a8 |
|---|---|:---:|:---:|:---:|
| Diffusion model | `diffusion_models/` | 40.5 GB | 21.2 GB | 13.4 GB |
| Text encoder | `text_encoders/` | 9.1 GB | 5.1 GB | 3.6 GB |
| Prompt upsampler | `text_encoders/` | 19.3 GB | 9.7 GB | 6.7 GB |
| VAE | `vae/` | 5.6 GB | 3.1 GB | – |
| LoRA for MiniMax-H3 | `loras/` | 2.0 GB | – | – |

| Set (model, text encoder, VAE) | Download | Peak VRAM at 8 MP |
|---|:---:|:---:|
| bf16 | 55 GB | 56 GB |
| int8 | 30 GB | 31 GB |
| w4a8, int8 VAE | **20 GB** | **21 GB** |

<p align="center">
  <img src="assets/weights.png" width="100%">
</p>

*Weights on disk. MiniMax-H3 counts its transformer, text encoder and video VAE.*

The int8 set stays very close to bf16, often almost pixel for pixel. The w4a8 set keeps the quality but changes more
of the details and sometimes the composition. On a 48 GB L40S, where the bf16 set has to offload, the w4a8 set renders a
2048 × 2048 image in 6.3 s instead of 19 s.

<p align="center">
  <img src="assets/quantization.jpg" width="100%">
</p>

*The same prompts and seed in bf16, int8 and w4a8, at 8 MP. The headers give the download size and the peak VRAM at
8 MP.*

The quantized files use ComfyUI's native formats, need no calibration data and run on comfy-kitchen's INT8 kernels, for
NVIDIA Ampere or newer and AMD RDNA3/4.

- **int8 (`int8_convrot`).** Weights are rotated with grouped Hadamard transforms to spread outliers, then stored as
  INT8 with per-row scales. Activations are quantized to INT8 on the fly.
- **w4a8.** The same rotation, then 4-bit weights on a 16-level codebook with an FP8 scale for every 16 inputs, and
  INT8 activations. The layers most sensitive to 4-bit weights stay in int8.
## Workflows
| Workflow | What it does |
|---|---|
| `p-h3-image_text_to_image.json` | Text-to-image at 8 MP from a short request |
| `p-h3-image_edit.json` | Edits an image, with optional reference images |
| `p-h3-image_lora_text_to_image.json` | Text-to-image with the LoRA on your own MiniMax-H3 |
| `p-h3-image_lora_edit.json` | Editing with the LoRA on your own MiniMax-H3 |
The workflows use only ComfyUI's own nodes. Load Diffusion Model loads the model, followed by ModelSamplingMiniMaxH3 at
1.0 for both shifts. Load CLIP (type `minimax`) loads the text encoder, Load VAE the VAE, and p-h3-image Conditioning
turns the prompt and the images into the conditioning and the latent. The prompt upsampler runs on Generate Text, and
sampling on ManualSigmas with the 8-step grid, Basic Guider, `euler` and Sampler Custom Advanced, with no CFG or
negative prompt. The LoRA loads with ComfyUI's Load LoRA (Bypass, Model Only).
## Recommended resolutions
<p align="center">
  <img src="assets/resolutions.png" width="100%">
</p>
| Aspect ratio | 8 MP (width × height) | 4 MP, for edits |
|:---:|:---:|:---:|
| 1:1 | **2912 × 2912** | 2048 × 2048 |
| 4:3 | **3360 × 2496** | 2368 × 1760 |
| 3:4 | **2496 × 3360** | 1760 × 2368 |
| 3:2 | **3552 × 2368** | 2496 × 1664 |
| 2:3 | **2368 × 3552** | 1664 × 2496 |
| 16:9 | **3872 × 2176** | 2720 × 1536 |
| 9:16 | **2176 × 3872** | 1536 × 2720 |
Text-to-image works best at 8 MP. In the workflows, Resolution Selector at 8 megapixels and a multiple of 32 gives
these sizes. Edits work best at 4 or 8 MP. In the edit workflows, Scale Image to Total Pixels brings `image_1`, the
image being edited, to 4 MP, and p-h3-image Conditioning generates the edit at its size unless `width` and `height` are
set. Reference images above about 8 MP are scaled down.
## Prompt upsampler
P-H3-Image is sensitive to prompting and renders full, specific prompts much better than short requests. The prompt
upsampler, based on Qwen3.5-9B, turns a one-line request into that prompt, and all example workflows use it. It thinks
about the request first and then writes the prompt.
It runs on ComfyUI's own nodes, the way FLUX.3 Klein's templates run theirs: Load CLIP (type `minimax`) and Generate
Text, with greedy decoding, so a request always gives the same prompt.
- **Text-to-image.** Format Text turns the request into the upsampler's input, `Aspect ratio: 1:1` and `Request: ...`
  on two lines, and Generate Text runs with `thinking` on. Keep the aspect ratio the same as in Resolution Selector.
- **Edits.** Format Text writes the upsampler's input with a `<Picture N>` block for every image, and the images reach
  Generate Text through Batch Images: `image_1` at 1 MP, the references padded to its size. The result is the edit
  prompt for p-h3-image Conditioning.
- **Use prompt upsampler**, an If/Else switch, set to false sends the request to the model as it is.

The upsampler runs before P-H3-Image, and ComfyUI moves it out of VRAM when P-H3-Image needs the memory. Its output is
cached, so it only runs again when the request or the images change.

| Upsampler file | Size | Peak VRAM | Time per prompt, L40S |
|---|:---:|:---:|:---:|
| `p-h3-image_prompt_upsampler_bf16` (recommended) | 19.3 GB | about 21 GB | about 7 s |
| `p-h3-image_prompt_upsampler_int8_convrot` | 9.7 GB | about 12 GB | about 13 s |
| `p-h3-image_prompt_upsampler_w4a8` | 6.7 GB | about 9 GB | about 11 s |

The w4a8 prompts differ most from bf16. Use the smaller files only when 21 GB does not fit.

## Editing

Connect the image to edit as `image_1` and up to 7 references after it, in the same order in Batch Images and on
p-h3-image Conditioning, with a `<Picture N>` block in Upsampler input for every image. The request can name the images
however you like, such as "the hat from the second photo".

<p align="center">
  <img src="assets/multi_image.jpg" width="100%">
</p>

*Top, eight public-domain portraits and the dinner party P-H3-Image composed from them, from a one-sentence request.
Bottom, eight scientists at a poker table, seven presidents wading through the swamp with an astronaut, and characters
from our own renders in the same swamp.*

## Already have MiniMax-H3?

If you run MiniMax-H3 in ComfyUI, the 2 GB LoRA `loras/p-h3-image_lora_bf16.safetensors` runs P-H3-Image on its FL2VA
transformer without a second large download. Load `minimax_h3_fl2va_bf16.safetensors` from
[Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3) (the pruned and quantized FL2VA files work too),
apply the LoRA with Load LoRA (Bypass, Model Only) at strength 1.0, and start from the `lora` workflows.

## Limitations

- **It is sensitive to prompting.** Keep the prompt upsampler in the graph. Hype words and very long prompts make
  images worse, and very short prompts give weak results without it.
- **Hands can break, and small people in the background can come out distorted.** Rendering at 8 MP helps.
- **Text is not fully reliable.** Small or dense text turns into pseudo-text, and longer passages sometimes get single
  letters wrong. Short quoted strings render well.
- **Quantized files are not identical to bf16.** int8 stays very close, w4a8 changes more of the details.

## License

The P-H3-Image weights are based on MiniMax-H3 and released under the [MiniMax H3 Community License](LICENSE). Please
read it before use. Among other terms, it excludes the European Union, the United Kingdom, the Republic of Korea and
the United States unless you have a separate license from MiniMax, and products built on it must show "Powered by
MiniMax H3". The text encoder's Qwen3-VL-4B parts and the prompt upsampler, based on Qwen3.5-9B, are under the
[Apache License 2.0](LICENSE-APACHE). See [NOTICE](NOTICE) for details.

## What's next?

- Compress your own models with [Pruna](https://github.com/PrunaAI/pruna) and give us a ⭐️ for more efficiency!
- Want to use our optimized image models right away? Check [P-Image-Ideogram](https://www.pruna.ai/p-image-ideogram) and [P-Image-Edit](https://www.pruna.ai/p-image-edit).

<style>
.model-button {
  display: inline-flex;
  flex-direction: row;
  justify-content: center;
  align-items: center;
  gap: 8px;

  padding: 8px 20px;
  border: none;
  border-radius: 8px;

  background: #9334e9;
  color: #ffffff;

  font-size: 14px;
  font-weight: 400;
  line-height: 1;
  text-decoration: none;
  white-space: nowrap;
  cursor: pointer;

  box-sizing: border-box;
  overflow: visible;
  opacity: 1;
}
</style>

<a href="https://dashboard.pruna.ai/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=hf_traffic" class="model-button">Try our models</a>

	---
	license: other
	license_name: minimax-h3-community-license-agreement
	license_link: LICENSE
	base_model: PrunaAI/p-h3-image
	base_model_relation: quantized
	pipeline_tag: text-to-image
	language:
	- en
	tags:
	- comfyui
	- diffusion-single-file
	- text-to-image
	- image-to-image
	- image-generation
	- image-editing
	- prompt-upsampling
	- lora
	- int8
	- 4-bit
	- minimax-h3
	- pruna-ai
	---
	<!-- header start -->
	<p align="center">
	<img src="assets/p-h3-image-comfy.jpg" width="800">
	</p>
	<!-- header end -->

	<p align="center">
	<a href="https://github.com/PrunaAI/pruna">
	<img src="https://img.shields.io/badge/GitHub-PrunaAI-9334E9?style=plastic&logo=github&logoColor=white" alt="GitHub">
	</a>

	<a href="https://twitter.com/PrunaAI">
	<img src="https://img.shields.io/badge/Twitter%2FX-@PrunaAI-9334E9?style=plastic&logo=x&logoColor=white" alt="Twitter/X">
	</a>

	<a href="https://www.linkedin.com/company/pruna-ai">
	<img src="https://img.shields.io/badge/LinkedIn-PrunaAI-9334E9?style=plastic&logo=linkedin&logoColor=white" alt="LinkedIn">
	</a>

	<a href="https://discord.com/invite/JFQmtFKCjd">
	<img src="https://img.shields.io/badge/Discord-Join%20us-9334E9?style=plastic&logo=discord&logoColor=white" alt="Discord">
	</a>

	<a href="https://dashboard.pruna.ai/login?utm_source=huggingface&utm_medium=org_card&utm_campaign=hf_traffic">
	<img src="https://img.shields.io/badge/Performance%20Models-Try%20them%20now-9334E9?style=plastic&logo=data:image/svg%2bxml;base64,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" alt="Performance Models">
	</a>
	</p>
	<div align="center">

	<h1 style="color: #9334E9;">P-H3-Image</h1>

	<h2>ComfyUI files for P-H3-Image, based on MiniMax-H3</h2>

	<h3>
	<span style="color: #9334E9;">bf16, int8 and w4a8</span>
	·
	<span style="color: #9334E9;">From 21 GB of VRAM</span>
	·
	<span style="color: #9334E9;">8 steps</span>
	·
	Text-to-image and editing with up to 8 images
	</h3>

	</div>

	This repository holds the ComfyUI files for P-H3-Image, an image model for text-to-image generation and image
	editing based on [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3). It renders 8-megapixel images in 8 steps
	without CFG and edits with up to 8 input images. Every component comes in bf16 and in ComfyUI's native int8 and 4-bit
	formats. The smallest set is a 20 GB download that peaks at 21 GB of VRAM at 8 MP, against 143 GB of weights for
	MiniMax-H3.

	ComfyUI supports P-H3-Image natively, no custom nodes needed. The diffusers pipeline is
	in [PrunaAI/P-H3-Image](https://huggingface.co/PrunaAI/P-H3-Image). Try it in the [Hugging Face Spaces](https://huggingface.co/spaces/PrunaAI/P-H3-Image). Read the full blog post [here](https://pruna.ai/blog/oss-p-h3-image-launch).

	## Quickstart

	1. Update ComfyUI. P-H3-Image support is on ComfyUI's master branch and ships with the next release. Until then,
	update to the latest ComfyUI from GitHub (nightly). The desktop app and Comfy Cloud follow stable releases and get it
	with the next one.

	```bash
	cd ComfyUI && git pull
	```

	2. Download one file per component into `ComfyUI/models`. The bf16 set, a 55 GB download plus the prompt upsampler,
	peaks at about 56 GB of VRAM:

	```bash
	hf download PrunaAI/P-H3-Image-comfy --include "diffusion_models/p-h3-image_bf16.safetensors" "text_encoders/p-h3-image_text_encoder_bf16.safetensors" "text_encoders/p-h3-image_prompt_upsampler_bf16.safetensors" "vae/p-h3-image_vae_bf16.safetensors" --local-dir ComfyUI/models
	```

	The smallest set, a 20 GB download plus the prompt upsampler, peaks at about 21 GB of VRAM:

	```bash
	hf download PrunaAI/P-H3-Image-Comfy --include "diffusion_models/p-h3-image_w4a8.safetensors" "text_encoders/p-h3-image_text_encoder_w4a8.safetensors" "text_encoders/p-h3-image_prompt_upsampler_bf16.safetensors" "vae/p-h3-image_vae_int8_convrot.safetensors" --local-dir ComfyUI/models
	```

	3. Open a workflow from `workflows/`, type a short request and run. The
	workflows render at 8 MP in 8 steps through the prompt upsampler.

	## Pick your files

	Pick one file per component. Files of different precisions can be mixed freely.

	\| Component \| Folder \| bf16 \| int8 (`int8_convrot`) \| w4a8 \|
	\|---\|---\|:---:\|:---:\|:---:\|
	\| Diffusion model \| `diffusion_models/` \| 40.5 GB \| 21.2 GB \| 13.4 GB \|
	\| Text encoder \| `text_encoders/` \| 9.1 GB \| 5.1 GB \| 3.6 GB \|
	\| Prompt upsampler \| `text_encoders/` \| 19.3 GB \| 9.7 GB \| 6.7 GB \|
	\| VAE \| `vae/` \| 5.6 GB \| 3.1 GB \| – \|
	\| LoRA for MiniMax-H3 \| `loras/` \| 2.0 GB \| – \| – \|

	\| Set (model, text encoder, VAE) \| Download \| Peak VRAM at 8 MP \|
	\|---\|:---:\|:---:\|
	\| bf16 \| 55 GB \| 56 GB \|
	\| int8 \| 30 GB \| 31 GB \|
	\| w4a8, int8 VAE \| 20 GB \| 21 GB \|

	<p align="center">
	<img src="assets/weights.png" width="100%">
	</p>

	Weights on disk. MiniMax-H3 counts its transformer, text encoder and video VAE.

	The int8 set stays very close to bf16, often almost pixel for pixel. The w4a8 set keeps the quality but changes more
	of the details and sometimes the composition. On a 48 GB L40S, where the bf16 set has to offload, the w4a8 set renders a
	2048 × 2048 image in 6.3 s instead of 19 s.

	<p align="center">
	<img src="assets/quantization.jpg" width="100%">
	</p>

	*The same prompts and seed in bf16, int8 and w4a8, at 8 MP. The headers give the download size and the peak VRAM at
	8 MP.*

	The quantized files use ComfyUI's native formats, need no calibration data and run on comfy-kitchen's INT8 kernels, for
	NVIDIA Ampere or newer and AMD RDNA3/4.

	- int8 (`int8_convrot`). Weights are rotated with grouped Hadamard transforms to spread outliers, then stored as
	INT8 with per-row scales. Activations are quantized to INT8 on the fly.
	- w4a8. The same rotation, then 4-bit weights on a 16-level codebook with an FP8 scale for every 16 inputs, and
	INT8 activations. The layers most sensitive to 4-bit weights stay in int8.

	## Workflows

	\| Workflow \| What it does \|
	\|---\|---\|
	\| `p-h3-image_text_to_image.json` \| Text-to-image at 8 MP from a short request \|
	\| `p-h3-image_edit.json` \| Edits an image, with optional reference images \|
	\| `p-h3-image_lora_text_to_image.json` \| Text-to-image with the LoRA on your own MiniMax-H3 \|
	\| `p-h3-image_lora_edit.json` \| Editing with the LoRA on your own MiniMax-H3 \|

	The workflows use only ComfyUI's own nodes. Load Diffusion Model loads the model, followed by ModelSamplingMiniMaxH3 at
	1.0 for both shifts. Load CLIP (type `minimax`) loads the text encoder, Load VAE the VAE, and p-h3-image Conditioning
	turns the prompt and the images into the conditioning and the latent. The prompt upsampler runs on Generate Text, and
	sampling on ManualSigmas with the 8-step grid, Basic Guider, `euler` and Sampler Custom Advanced, with no CFG or
	negative prompt. The LoRA loads with ComfyUI's Load LoRA (Bypass, Model Only).

	## Recommended resolutions

	<p align="center">
	<img src="assets/resolutions.png" width="100%">
	</p>

	\| Aspect ratio \| 8 MP (width × height) \| 4 MP, for edits \|
	\|:---:\|:---:\|:---:\|
	\| 1:1 \| 2912 × 2912 \| 2048 × 2048 \|
	\| 4:3 \| 3360 × 2496 \| 2368 × 1760 \|
	\| 3:4 \| 2496 × 3360 \| 1760 × 2368 \|
	\| 3:2 \| 3552 × 2368 \| 2496 × 1664 \|
	\| 2:3 \| 2368 × 3552 \| 1664 × 2496 \|
	\| 16:9 \| 3872 × 2176 \| 2720 × 1536 \|
	\| 9:16 \| 2176 × 3872 \| 1536 × 2720 \|

	Text-to-image works best at 8 MP. In the workflows, Resolution Selector at 8 megapixels and a multiple of 32 gives
	these sizes. Edits work best at 4 or 8 MP. In the edit workflows, Scale Image to Total Pixels brings `image_1`, the
	image being edited, to 4 MP, and p-h3-image Conditioning generates the edit at its size unless `width` and `height` are
	set. Reference images above about 8 MP are scaled down.

	## Prompt upsampler

	P-H3-Image is sensitive to prompting and renders full, specific prompts much better than short requests. The prompt
	upsampler, based on Qwen3.5-9B, turns a one-line request into that prompt, and all example workflows use it. It thinks
	about the request first and then writes the prompt.

	It runs on ComfyUI's own nodes, the way FLUX.3 Klein's templates run theirs: Load CLIP (type `minimax`) and Generate
	Text, with greedy decoding, so a request always gives the same prompt.

	- Text-to-image. Format Text turns the request into the upsampler's input, `Aspect ratio: 1:1` and `Request: ...`
	on two lines, and Generate Text runs with `thinking` on. Keep the aspect ratio the same as in Resolution Selector.
	- Edits. Format Text writes the upsampler's input with a `<Picture N>` block for every image, and the images reach
	Generate Text through Batch Images: `image_1` at 1 MP, the references padded to its size. The result is the edit
	prompt for p-h3-image Conditioning.
	- Use prompt upsampler, an If/Else switch, set to false sends the request to the model as it is.

	The upsampler runs before P-H3-Image, and ComfyUI moves it out of VRAM when P-H3-Image needs the memory. Its output is
	cached, so it only runs again when the request or the images change.

	\| Upsampler file \| Size \| Peak VRAM \| Time per prompt, L40S \|
	\|---\|:---:\|:---:\|:---:\|
	\| `p-h3-image_prompt_upsampler_bf16` (recommended) \| 19.3 GB \| about 21 GB \| about 7 s \|
	\| `p-h3-image_prompt_upsampler_int8_convrot` \| 9.7 GB \| about 12 GB \| about 13 s \|
	\| `p-h3-image_prompt_upsampler_w4a8` \| 6.7 GB \| about 9 GB \| about 11 s \|

	The w4a8 prompts differ most from bf16. Use the smaller files only when 21 GB does not fit.

	## Editing

	Connect the image to edit as `image_1` and up to 7 references after it, in the same order in Batch Images and on
	p-h3-image Conditioning, with a `<Picture N>` block in Upsampler input for every image. The request can name the images
	however you like, such as "the hat from the second photo".

	<p align="center">
	<img src="assets/multi_image.jpg" width="100%">
	</p>

	*Top, eight public-domain portraits and the dinner party P-H3-Image composed from them, from a one-sentence request.
	Bottom, eight scientists at a poker table, seven presidents wading through the swamp with an astronaut, and characters
	from our own renders in the same swamp.*

	## Already have MiniMax-H3?

	If you run MiniMax-H3 in ComfyUI, the 2 GB LoRA `loras/p-h3-image_lora_bf16.safetensors` runs P-H3-Image on its FL2VA
	transformer without a second large download. Load `minimax_h3_fl2va_bf16.safetensors` from
	[Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3) (the pruned and quantized FL2VA files work too),
	apply the LoRA with Load LoRA (Bypass, Model Only) at strength 1.0, and start from the `lora` workflows.

	## Limitations

	- It is sensitive to prompting. Keep the prompt upsampler in the graph. Hype words and very long prompts make
	images worse, and very short prompts give weak results without it.
	- Hands can break, and small people in the background can come out distorted. Rendering at 8 MP helps.
	- Text is not fully reliable. Small or dense text turns into pseudo-text, and longer passages sometimes get single
	letters wrong. Short quoted strings render well.
	- Quantized files are not identical to bf16. int8 stays very close, w4a8 changes more of the details.

	## License

	The P-H3-Image weights are based on MiniMax-H3 and released under the [MiniMax H3 Community License](LICENSE). Please
	read it before use. Among other terms, it excludes the European Union, the United Kingdom, the Republic of Korea and
	the United States unless you have a separate license from MiniMax, and products built on it must show "Powered by
	MiniMax H3". The text encoder's Qwen3-VL-4B parts and the prompt upsampler, based on Qwen3.5-9B, are under the
	[Apache License 2.0](LICENSE-APACHE). See [NOTICE](NOTICE) for details.

	## What's next?

	- Compress your own models with [Pruna](https://github.com/PrunaAI/pruna) and give us a ⭐️ for more efficiency!
	- Want to use our optimized image models right away? Check [P-Image-Ideogram](https://www.pruna.ai/p-image-ideogram) and [P-Image-Edit](https://www.pruna.ai/p-image-edit).

	<style>
	.model-button {
	display: inline-flex;
	flex-direction: row;
	justify-content: center;
	align-items: center;
	gap: 8px;

	padding: 8px 20px;
	border: none;
	border-radius: 8px;

	background: #9334e9;
	color: #ffffff;

	font-size: 14px;
	font-weight: 400;
	line-height: 1;
	text-decoration: none;
	white-space: nowrap;
	cursor: pointer;

	box-sizing: border-box;
	overflow: visible;
	opacity: 1;
	}
	</style>

	<a href="https://dashboard.pruna.ai/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=hf_traffic" class="model-button">Try our models</a>