Text-to-Image
Diffusion Single File
MiniMax H3
Pruna AI
English
comfyui
image-to-image
image-generation
image-editing
prompt-upsampling
lora
int8
4-bit precision
Instructions to use PrunaAI/P-Image-OSS-Comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use PrunaAI/P-Image-OSS-Comfy with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Pruna AI
How to use PrunaAI/P-Image-OSS-Comfy with Pruna AI:
from pruna import PrunaModel model = PrunaModel.from_pretrained("PrunaAI/P-Image-OSS-Comfy") - Notebooks
- Google Colab
- Kaggle
Update naming and assets
Browse files- .gitattributes +1 -1
- NOTICE +3 -3
- README.md +19 -19
- assets/{p-h3-image-comfy.jpg → p-image-oss-comfy.jpg} +2 -2
- assets/weights.png +0 -0
- workflows/{p-h3-image_edit.json → p-image-oss_edit.json} +8 -8
- workflows/{p-h3-image_lora_edit.json → p-image-oss_lora_edit.json} +8 -8
- workflows/{p-h3-image_lora_text_to_image.json → p-image-oss_lora_text_to_image.json} +8 -8
- workflows/{p-h3-image_text_to_image.json → p-image-oss_text_to_image.json} +8 -8
.gitattributes
CHANGED
|
@@ -34,5 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
assets/multi_image.jpg filter=lfs diff=lfs merge=lfs -text
|
| 37 |
-
assets/p-
|
| 38 |
assets/quantization.jpg filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
assets/multi_image.jpg filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
assets/p-image-oss-comfy.jpg filter=lfs diff=lfs merge=lfs -text
|
| 38 |
assets/quantization.jpg filter=lfs diff=lfs merge=lfs -text
|
NOTICE
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
-
p-
|
| 2 |
Copyright 2026 Pruna AI
|
| 3 |
|
| 4 |
The files in this repository were modified by Pruna AI.
|
| 5 |
|
| 6 |
diffusion_models/, loras/, vae/ and text_encoders/p-h3-image_text_encoder_*.safetensors
|
| 7 |
-
p-
|
| 8 |
Community License Agreement, see LICENSE. The text encoder is also based on Qwen3-VL-4B by the Qwen team
|
| 9 |
(https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct); its Qwen3-VL-4B parts are under the Apache License 2.0, see
|
| 10 |
LICENSE-APACHE.
|
| 11 |
|
| 12 |
text_encoders/p-h3-image_prompt_upsampler_*.safetensors
|
| 13 |
-
The p-
|
| 14 |
under the Apache License 2.0, see LICENSE-APACHE.
|
|
|
|
| 1 |
+
p-image-oss for ComfyUI
|
| 2 |
Copyright 2026 Pruna AI
|
| 3 |
|
| 4 |
The files in this repository were modified by Pruna AI.
|
| 5 |
|
| 6 |
diffusion_models/, loras/, vae/ and text_encoders/p-h3-image_text_encoder_*.safetensors
|
| 7 |
+
p-image-oss, based on MiniMax-H3 by MiniMax (https://huggingface.co/MiniMaxAI/MiniMax-H3), under the MiniMax H3
|
| 8 |
Community License Agreement, see LICENSE. The text encoder is also based on Qwen3-VL-4B by the Qwen team
|
| 9 |
(https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct); its Qwen3-VL-4B parts are under the Apache License 2.0, see
|
| 10 |
LICENSE-APACHE.
|
| 11 |
|
| 12 |
text_encoders/p-h3-image_prompt_upsampler_*.safetensors
|
| 13 |
+
The p-image-oss prompt upsampler, based on Qwen3.5-9B by the Qwen team (https://huggingface.co/Qwen/Qwen3.5-9B),
|
| 14 |
under the Apache License 2.0, see LICENSE-APACHE.
|
README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
license: other
|
| 3 |
license_name: minimax-h3-community-license-agreement
|
| 4 |
license_link: LICENSE
|
| 5 |
-
base_model: PrunaAI/
|
| 6 |
base_model_relation: quantized
|
| 7 |
pipeline_tag: text-to-image
|
| 8 |
language:
|
|
@@ -23,7 +23,7 @@ tags:
|
|
| 23 |
---
|
| 24 |
<!-- header start -->
|
| 25 |
<p align="center">
|
| 26 |
-
<img src="assets/p-
|
| 27 |
</p>
|
| 28 |
<!-- header end -->
|
| 29 |
|
|
@@ -50,9 +50,9 @@ tags:
|
|
| 50 |
</p>
|
| 51 |
<div align="center">
|
| 52 |
|
| 53 |
-
<h1 style="color: #9334E9;">P-
|
| 54 |
|
| 55 |
-
<h2>ComfyUI files for P-
|
| 56 |
|
| 57 |
<h3>
|
| 58 |
<span style="color: #9334E9;">bf16, int8 and w4a8</span>
|
|
@@ -66,18 +66,18 @@ tags:
|
|
| 66 |
|
| 67 |
</div>
|
| 68 |
|
| 69 |
-
This repository holds the ComfyUI files for **P-
|
| 70 |
editing based on [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3). It renders 8-megapixel images in 8 steps
|
| 71 |
without CFG and edits with up to 8 input images. Every component comes in bf16 and in ComfyUI's native int8 and 4-bit
|
| 72 |
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
|
| 73 |
MiniMax-H3.
|
| 74 |
|
| 75 |
-
ComfyUI supports P-
|
| 76 |
-
in [PrunaAI/P-
|
| 77 |
|
| 78 |
## Quickstart
|
| 79 |
|
| 80 |
-
1. **Update ComfyUI.** P-
|
| 81 |
update to the latest ComfyUI from GitHub (nightly). The desktop app and Comfy Cloud follow stable releases and get it
|
| 82 |
with the next one.
|
| 83 |
|
|
@@ -89,13 +89,13 @@ in [PrunaAI/P-H3-Image](https://huggingface.co/PrunaAI/P-H3-Image). Try it in th
|
|
| 89 |
peaks at about 56 GB of VRAM:
|
| 90 |
|
| 91 |
```bash
|
| 92 |
-
hf download PrunaAI/P-
|
| 93 |
```
|
| 94 |
|
| 95 |
The smallest set, a 20 GB download plus the prompt upsampler, peaks at about 21 GB of VRAM:
|
| 96 |
|
| 97 |
```bash
|
| 98 |
-
hf download PrunaAI/P-
|
| 99 |
```
|
| 100 |
|
| 101 |
3. **Open a workflow** from `workflows/`, type a short request and run. The
|
|
@@ -148,10 +148,10 @@ NVIDIA Ampere or newer and AMD RDNA3/4.
|
|
| 148 |
|
| 149 |
| Workflow | What it does |
|
| 150 |
|---|---|
|
| 151 |
-
| `p-
|
| 152 |
-
| `p-
|
| 153 |
-
| `p-
|
| 154 |
-
| `p-
|
| 155 |
|
| 156 |
The workflows use only ComfyUI's own nodes. Load Diffusion Model loads the model, followed by ModelSamplingMiniMaxH3 at
|
| 157 |
1.0 for both shifts. Load CLIP (type `minimax`) loads the text encoder, Load VAE the VAE, and p-h3-image Conditioning
|
|
@@ -182,7 +182,7 @@ set. Reference images above about 8 MP are scaled down.
|
|
| 182 |
|
| 183 |
## Prompt upsampler
|
| 184 |
|
| 185 |
-
P-
|
| 186 |
upsampler, based on Qwen3.5-9B, turns a one-line request into that prompt, and all example workflows use it. It thinks
|
| 187 |
about the request first and then writes the prompt.
|
| 188 |
|
|
@@ -196,7 +196,7 @@ Text, with greedy decoding, so a request always gives the same prompt.
|
|
| 196 |
prompt for p-h3-image Conditioning.
|
| 197 |
- **Use prompt upsampler**, an If/Else switch, set to false sends the request to the model as it is.
|
| 198 |
|
| 199 |
-
The upsampler runs before P-
|
| 200 |
cached, so it only runs again when the request or the images change.
|
| 201 |
|
| 202 |
| Upsampler file | Size | Peak VRAM | Time per prompt, L40S |
|
|
@@ -217,13 +217,13 @@ however you like, such as "the hat from the second photo".
|
|
| 217 |
<img src="assets/multi_image.jpg" width="100%">
|
| 218 |
</p>
|
| 219 |
|
| 220 |
-
*Top, eight public-domain portraits and the dinner party P-
|
| 221 |
Bottom, eight scientists at a poker table, seven presidents wading through the swamp with an astronaut, and characters
|
| 222 |
from our own renders in the same swamp.*
|
| 223 |
|
| 224 |
## Already have MiniMax-H3?
|
| 225 |
|
| 226 |
-
If you run MiniMax-H3 in ComfyUI, the 2 GB LoRA `loras/p-h3-image_lora_bf16.safetensors` runs P-
|
| 227 |
transformer without a second large download. Load `minimax_h3_fl2va_bf16.safetensors` from
|
| 228 |
[Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3) (the pruned and quantized FL2VA files work too),
|
| 229 |
apply the LoRA with Load LoRA (Bypass, Model Only) at strength 1.0, and start from the `lora` workflows.
|
|
@@ -239,7 +239,7 @@ apply the LoRA with Load LoRA (Bypass, Model Only) at strength 1.0, and start fr
|
|
| 239 |
|
| 240 |
## License
|
| 241 |
|
| 242 |
-
The P-
|
| 243 |
read it before use. Among other terms, it excludes the European Union, the United Kingdom, the Republic of Korea and
|
| 244 |
the United States unless you have a separate license from MiniMax, and products built on it must show "Powered by
|
| 245 |
MiniMax H3". The text encoder's Qwen3-VL-4B parts and the prompt upsampler, based on Qwen3.5-9B, are under the
|
|
|
|
| 2 |
license: other
|
| 3 |
license_name: minimax-h3-community-license-agreement
|
| 4 |
license_link: LICENSE
|
| 5 |
+
base_model: PrunaAI/P-Image-OSS
|
| 6 |
base_model_relation: quantized
|
| 7 |
pipeline_tag: text-to-image
|
| 8 |
language:
|
|
|
|
| 23 |
---
|
| 24 |
<!-- header start -->
|
| 25 |
<p align="center">
|
| 26 |
+
<img src="assets/p-image-oss-comfy.jpg" width="800">
|
| 27 |
</p>
|
| 28 |
<!-- header end -->
|
| 29 |
|
|
|
|
| 50 |
</p>
|
| 51 |
<div align="center">
|
| 52 |
|
| 53 |
+
<h1 style="color: #9334E9;">P-Image-OSS</h1>
|
| 54 |
|
| 55 |
+
<h2>ComfyUI files for P-Image-OSS, based on MiniMax-H3</h2>
|
| 56 |
|
| 57 |
<h3>
|
| 58 |
<span style="color: #9334E9;">bf16, int8 and w4a8</span>
|
|
|
|
| 66 |
|
| 67 |
</div>
|
| 68 |
|
| 69 |
+
This repository holds the ComfyUI files for **P-Image-OSS**, an image model for text-to-image generation and image
|
| 70 |
editing based on [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3). It renders 8-megapixel images in 8 steps
|
| 71 |
without CFG and edits with up to 8 input images. Every component comes in bf16 and in ComfyUI's native int8 and 4-bit
|
| 72 |
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
|
| 73 |
MiniMax-H3.
|
| 74 |
|
| 75 |
+
ComfyUI supports P-Image-OSS natively, no custom nodes needed. The diffusers pipeline is
|
| 76 |
+
in [PrunaAI/P-Image-OSS](https://huggingface.co/PrunaAI/P-Image-OSS). Try it in the [Hugging Face Spaces](https://huggingface.co/spaces/PrunaAI/P-Image-OSS). Read the full blog post [here](https://pruna.ai/blog/oss-p-h3-image-launch).
|
| 77 |
|
| 78 |
## Quickstart
|
| 79 |
|
| 80 |
+
1. **Update ComfyUI.** P-Image-OSS support is on ComfyUI's master branch and ships with the next release. Until then,
|
| 81 |
update to the latest ComfyUI from GitHub (nightly). The desktop app and Comfy Cloud follow stable releases and get it
|
| 82 |
with the next one.
|
| 83 |
|
|
|
|
| 89 |
peaks at about 56 GB of VRAM:
|
| 90 |
|
| 91 |
```bash
|
| 92 |
+
hf download PrunaAI/P-Image-OSS-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
|
| 93 |
```
|
| 94 |
|
| 95 |
The smallest set, a 20 GB download plus the prompt upsampler, peaks at about 21 GB of VRAM:
|
| 96 |
|
| 97 |
```bash
|
| 98 |
+
hf download PrunaAI/P-Image-OSS-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
|
| 99 |
```
|
| 100 |
|
| 101 |
3. **Open a workflow** from `workflows/`, type a short request and run. The
|
|
|
|
| 148 |
|
| 149 |
| Workflow | What it does |
|
| 150 |
|---|---|
|
| 151 |
+
| `p-image-oss_text_to_image.json` | Text-to-image at 8 MP from a short request |
|
| 152 |
+
| `p-image-oss_edit.json` | Edits an image, with optional reference images |
|
| 153 |
+
| `p-image-oss_lora_text_to_image.json` | Text-to-image with the LoRA on your own MiniMax-H3 |
|
| 154 |
+
| `p-image-oss_lora_edit.json` | Editing with the LoRA on your own MiniMax-H3 |
|
| 155 |
|
| 156 |
The workflows use only ComfyUI's own nodes. Load Diffusion Model loads the model, followed by ModelSamplingMiniMaxH3 at
|
| 157 |
1.0 for both shifts. Load CLIP (type `minimax`) loads the text encoder, Load VAE the VAE, and p-h3-image Conditioning
|
|
|
|
| 182 |
|
| 183 |
## Prompt upsampler
|
| 184 |
|
| 185 |
+
P-Image-OSS is sensitive to prompting and renders full, specific prompts much better than short requests. The prompt
|
| 186 |
upsampler, based on Qwen3.5-9B, turns a one-line request into that prompt, and all example workflows use it. It thinks
|
| 187 |
about the request first and then writes the prompt.
|
| 188 |
|
|
|
|
| 196 |
prompt for p-h3-image Conditioning.
|
| 197 |
- **Use prompt upsampler**, an If/Else switch, set to false sends the request to the model as it is.
|
| 198 |
|
| 199 |
+
The upsampler runs before P-Image-OSS, and ComfyUI moves it out of VRAM when P-Image-OSS needs the memory. Its output is
|
| 200 |
cached, so it only runs again when the request or the images change.
|
| 201 |
|
| 202 |
| Upsampler file | Size | Peak VRAM | Time per prompt, L40S |
|
|
|
|
| 217 |
<img src="assets/multi_image.jpg" width="100%">
|
| 218 |
</p>
|
| 219 |
|
| 220 |
+
*Top, eight public-domain portraits and the dinner party P-Image-OSS composed from them, from a one-sentence request.
|
| 221 |
Bottom, eight scientists at a poker table, seven presidents wading through the swamp with an astronaut, and characters
|
| 222 |
from our own renders in the same swamp.*
|
| 223 |
|
| 224 |
## Already have MiniMax-H3?
|
| 225 |
|
| 226 |
+
If you run MiniMax-H3 in ComfyUI, the 2 GB LoRA `loras/p-h3-image_lora_bf16.safetensors` runs P-Image-OSS on its FL2VA
|
| 227 |
transformer without a second large download. Load `minimax_h3_fl2va_bf16.safetensors` from
|
| 228 |
[Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3) (the pruned and quantized FL2VA files work too),
|
| 229 |
apply the LoRA with Load LoRA (Bypass, Model Only) at strength 1.0, and start from the `lora` workflows.
|
|
|
|
| 239 |
|
| 240 |
## License
|
| 241 |
|
| 242 |
+
The P-Image-OSS weights are based on MiniMax-H3 and released under the [MiniMax H3 Community License](LICENSE). Please
|
| 243 |
read it before use. Among other terms, it excludes the European Union, the United Kingdom, the Republic of Korea and
|
| 244 |
the United States unless you have a separate license from MiniMax, and products built on it must show "Powered by
|
| 245 |
MiniMax H3". The text encoder's Qwen3-VL-4B parts and the prompt upsampler, based on Qwen3.5-9B, are under the
|
assets/{p-h3-image-comfy.jpg → p-image-oss-comfy.jpg}
RENAMED
|
File without changes
|
assets/weights.png
CHANGED
|
|
workflows/{p-h3-image_edit.json → p-image-oss_edit.json}
RENAMED
|
@@ -480,10 +480,10 @@
|
|
| 480 |
"ver": "0.43.0"
|
| 481 |
},
|
| 482 |
"widgets_values": [
|
| 483 |
-
"p-
|
| 484 |
],
|
| 485 |
"widgets_values_named": {
|
| 486 |
-
"filename_prefix": "p-
|
| 487 |
}
|
| 488 |
},
|
| 489 |
{
|
|
@@ -540,7 +540,7 @@
|
|
| 540 |
]
|
| 541 |
}
|
| 542 |
],
|
| 543 |
-
"title": "p-
|
| 544 |
"properties": {
|
| 545 |
"Node name for S&R": "CLIPLoader",
|
| 546 |
"cnr_id": "comfy-core",
|
|
@@ -548,7 +548,7 @@
|
|
| 548 |
"models": [
|
| 549 |
{
|
| 550 |
"name": "p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 551 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 552 |
"directory": "text_encoders"
|
| 553 |
}
|
| 554 |
]
|
|
@@ -1251,7 +1251,7 @@
|
|
| 1251 |
"models": [
|
| 1252 |
{
|
| 1253 |
"name": "p-h3-image_bf16.safetensors",
|
| 1254 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 1255 |
"directory": "diffusion_models"
|
| 1256 |
}
|
| 1257 |
]
|
|
@@ -1381,13 +1381,13 @@
|
|
| 1381 |
]
|
| 1382 |
}
|
| 1383 |
],
|
| 1384 |
-
"title": "p-
|
| 1385 |
"properties": {
|
| 1386 |
"Node name for S&R": "CLIPLoader",
|
| 1387 |
"models": [
|
| 1388 |
{
|
| 1389 |
"name": "p-h3-image_text_encoder_bf16.safetensors",
|
| 1390 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 1391 |
"directory": "text_encoders"
|
| 1392 |
}
|
| 1393 |
]
|
|
@@ -1444,7 +1444,7 @@
|
|
| 1444 |
"models": [
|
| 1445 |
{
|
| 1446 |
"name": "p-h3-image_vae_bf16.safetensors",
|
| 1447 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 1448 |
"directory": "vae"
|
| 1449 |
}
|
| 1450 |
]
|
|
|
|
| 480 |
"ver": "0.43.0"
|
| 481 |
},
|
| 482 |
"widgets_values": [
|
| 483 |
+
"p-image-oss"
|
| 484 |
],
|
| 485 |
"widgets_values_named": {
|
| 486 |
+
"filename_prefix": "p-image-oss"
|
| 487 |
}
|
| 488 |
},
|
| 489 |
{
|
|
|
|
| 540 |
]
|
| 541 |
}
|
| 542 |
],
|
| 543 |
+
"title": "p-image-oss prompt upsampler",
|
| 544 |
"properties": {
|
| 545 |
"Node name for S&R": "CLIPLoader",
|
| 546 |
"cnr_id": "comfy-core",
|
|
|
|
| 548 |
"models": [
|
| 549 |
{
|
| 550 |
"name": "p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 551 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/text_encoders/p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 552 |
"directory": "text_encoders"
|
| 553 |
}
|
| 554 |
]
|
|
|
|
| 1251 |
"models": [
|
| 1252 |
{
|
| 1253 |
"name": "p-h3-image_bf16.safetensors",
|
| 1254 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/diffusion_models/p-h3-image_bf16.safetensors",
|
| 1255 |
"directory": "diffusion_models"
|
| 1256 |
}
|
| 1257 |
]
|
|
|
|
| 1381 |
]
|
| 1382 |
}
|
| 1383 |
],
|
| 1384 |
+
"title": "p-image-oss text encoder",
|
| 1385 |
"properties": {
|
| 1386 |
"Node name for S&R": "CLIPLoader",
|
| 1387 |
"models": [
|
| 1388 |
{
|
| 1389 |
"name": "p-h3-image_text_encoder_bf16.safetensors",
|
| 1390 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/text_encoders/p-h3-image_text_encoder_bf16.safetensors",
|
| 1391 |
"directory": "text_encoders"
|
| 1392 |
}
|
| 1393 |
]
|
|
|
|
| 1444 |
"models": [
|
| 1445 |
{
|
| 1446 |
"name": "p-h3-image_vae_bf16.safetensors",
|
| 1447 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/vae/p-h3-image_vae_bf16.safetensors",
|
| 1448 |
"directory": "vae"
|
| 1449 |
}
|
| 1450 |
]
|
workflows/{p-h3-image_lora_edit.json → p-image-oss_lora_edit.json}
RENAMED
|
@@ -545,10 +545,10 @@
|
|
| 545 |
"ver": "0.43.0"
|
| 546 |
},
|
| 547 |
"widgets_values": [
|
| 548 |
-
"p-
|
| 549 |
],
|
| 550 |
"widgets_values_named": {
|
| 551 |
-
"filename_prefix": "p-
|
| 552 |
}
|
| 553 |
},
|
| 554 |
{
|
|
@@ -608,7 +608,7 @@
|
|
| 608 |
"models": [
|
| 609 |
{
|
| 610 |
"name": "p-h3-image_lora_bf16.safetensors",
|
| 611 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 612 |
"directory": "loras"
|
| 613 |
}
|
| 614 |
]
|
|
@@ -740,7 +740,7 @@
|
|
| 740 |
]
|
| 741 |
}
|
| 742 |
],
|
| 743 |
-
"title": "p-
|
| 744 |
"properties": {
|
| 745 |
"Node name for S&R": "CLIPLoader",
|
| 746 |
"cnr_id": "comfy-core",
|
|
@@ -748,7 +748,7 @@
|
|
| 748 |
"models": [
|
| 749 |
{
|
| 750 |
"name": "p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 751 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 752 |
"directory": "text_encoders"
|
| 753 |
}
|
| 754 |
]
|
|
@@ -1456,13 +1456,13 @@
|
|
| 1456 |
]
|
| 1457 |
}
|
| 1458 |
],
|
| 1459 |
-
"title": "p-
|
| 1460 |
"properties": {
|
| 1461 |
"Node name for S&R": "CLIPLoader",
|
| 1462 |
"models": [
|
| 1463 |
{
|
| 1464 |
"name": "p-h3-image_text_encoder_bf16.safetensors",
|
| 1465 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 1466 |
"directory": "text_encoders"
|
| 1467 |
}
|
| 1468 |
]
|
|
@@ -1519,7 +1519,7 @@
|
|
| 1519 |
"models": [
|
| 1520 |
{
|
| 1521 |
"name": "p-h3-image_vae_bf16.safetensors",
|
| 1522 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 1523 |
"directory": "vae"
|
| 1524 |
}
|
| 1525 |
]
|
|
|
|
| 545 |
"ver": "0.43.0"
|
| 546 |
},
|
| 547 |
"widgets_values": [
|
| 548 |
+
"p-image-oss"
|
| 549 |
],
|
| 550 |
"widgets_values_named": {
|
| 551 |
+
"filename_prefix": "p-image-oss"
|
| 552 |
}
|
| 553 |
},
|
| 554 |
{
|
|
|
|
| 608 |
"models": [
|
| 609 |
{
|
| 610 |
"name": "p-h3-image_lora_bf16.safetensors",
|
| 611 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/loras/p-h3-image_lora_bf16.safetensors",
|
| 612 |
"directory": "loras"
|
| 613 |
}
|
| 614 |
]
|
|
|
|
| 740 |
]
|
| 741 |
}
|
| 742 |
],
|
| 743 |
+
"title": "p-image-oss prompt upsampler",
|
| 744 |
"properties": {
|
| 745 |
"Node name for S&R": "CLIPLoader",
|
| 746 |
"cnr_id": "comfy-core",
|
|
|
|
| 748 |
"models": [
|
| 749 |
{
|
| 750 |
"name": "p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 751 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/text_encoders/p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 752 |
"directory": "text_encoders"
|
| 753 |
}
|
| 754 |
]
|
|
|
|
| 1456 |
]
|
| 1457 |
}
|
| 1458 |
],
|
| 1459 |
+
"title": "p-image-oss text encoder",
|
| 1460 |
"properties": {
|
| 1461 |
"Node name for S&R": "CLIPLoader",
|
| 1462 |
"models": [
|
| 1463 |
{
|
| 1464 |
"name": "p-h3-image_text_encoder_bf16.safetensors",
|
| 1465 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/text_encoders/p-h3-image_text_encoder_bf16.safetensors",
|
| 1466 |
"directory": "text_encoders"
|
| 1467 |
}
|
| 1468 |
]
|
|
|
|
| 1519 |
"models": [
|
| 1520 |
{
|
| 1521 |
"name": "p-h3-image_vae_bf16.safetensors",
|
| 1522 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/vae/p-h3-image_vae_bf16.safetensors",
|
| 1523 |
"directory": "vae"
|
| 1524 |
}
|
| 1525 |
]
|
workflows/{p-h3-image_lora_text_to_image.json → p-image-oss_lora_text_to_image.json}
RENAMED
|
@@ -413,10 +413,10 @@
|
|
| 413 |
"ver": "0.43.0"
|
| 414 |
},
|
| 415 |
"widgets_values": [
|
| 416 |
-
"p-
|
| 417 |
],
|
| 418 |
"widgets_values_named": {
|
| 419 |
-
"filename_prefix": "p-
|
| 420 |
}
|
| 421 |
},
|
| 422 |
{
|
|
@@ -476,7 +476,7 @@
|
|
| 476 |
"models": [
|
| 477 |
{
|
| 478 |
"name": "p-h3-image_lora_bf16.safetensors",
|
| 479 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 480 |
"directory": "loras"
|
| 481 |
}
|
| 482 |
]
|
|
@@ -608,7 +608,7 @@
|
|
| 608 |
]
|
| 609 |
}
|
| 610 |
],
|
| 611 |
-
"title": "p-
|
| 612 |
"properties": {
|
| 613 |
"Node name for S&R": "CLIPLoader",
|
| 614 |
"cnr_id": "comfy-core",
|
|
@@ -616,7 +616,7 @@
|
|
| 616 |
"models": [
|
| 617 |
{
|
| 618 |
"name": "p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 619 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 620 |
"directory": "text_encoders"
|
| 621 |
}
|
| 622 |
]
|
|
@@ -1149,13 +1149,13 @@
|
|
| 1149 |
]
|
| 1150 |
}
|
| 1151 |
],
|
| 1152 |
-
"title": "p-
|
| 1153 |
"properties": {
|
| 1154 |
"Node name for S&R": "CLIPLoader",
|
| 1155 |
"models": [
|
| 1156 |
{
|
| 1157 |
"name": "p-h3-image_text_encoder_bf16.safetensors",
|
| 1158 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 1159 |
"directory": "text_encoders"
|
| 1160 |
}
|
| 1161 |
]
|
|
@@ -1211,7 +1211,7 @@
|
|
| 1211 |
"models": [
|
| 1212 |
{
|
| 1213 |
"name": "p-h3-image_vae_bf16.safetensors",
|
| 1214 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 1215 |
"directory": "vae"
|
| 1216 |
}
|
| 1217 |
]
|
|
|
|
| 413 |
"ver": "0.43.0"
|
| 414 |
},
|
| 415 |
"widgets_values": [
|
| 416 |
+
"p-image-oss"
|
| 417 |
],
|
| 418 |
"widgets_values_named": {
|
| 419 |
+
"filename_prefix": "p-image-oss"
|
| 420 |
}
|
| 421 |
},
|
| 422 |
{
|
|
|
|
| 476 |
"models": [
|
| 477 |
{
|
| 478 |
"name": "p-h3-image_lora_bf16.safetensors",
|
| 479 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/loras/p-h3-image_lora_bf16.safetensors",
|
| 480 |
"directory": "loras"
|
| 481 |
}
|
| 482 |
]
|
|
|
|
| 608 |
]
|
| 609 |
}
|
| 610 |
],
|
| 611 |
+
"title": "p-image-oss prompt upsampler",
|
| 612 |
"properties": {
|
| 613 |
"Node name for S&R": "CLIPLoader",
|
| 614 |
"cnr_id": "comfy-core",
|
|
|
|
| 616 |
"models": [
|
| 617 |
{
|
| 618 |
"name": "p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 619 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/text_encoders/p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 620 |
"directory": "text_encoders"
|
| 621 |
}
|
| 622 |
]
|
|
|
|
| 1149 |
]
|
| 1150 |
}
|
| 1151 |
],
|
| 1152 |
+
"title": "p-image-oss text encoder",
|
| 1153 |
"properties": {
|
| 1154 |
"Node name for S&R": "CLIPLoader",
|
| 1155 |
"models": [
|
| 1156 |
{
|
| 1157 |
"name": "p-h3-image_text_encoder_bf16.safetensors",
|
| 1158 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/text_encoders/p-h3-image_text_encoder_bf16.safetensors",
|
| 1159 |
"directory": "text_encoders"
|
| 1160 |
}
|
| 1161 |
]
|
|
|
|
| 1211 |
"models": [
|
| 1212 |
{
|
| 1213 |
"name": "p-h3-image_vae_bf16.safetensors",
|
| 1214 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/vae/p-h3-image_vae_bf16.safetensors",
|
| 1215 |
"directory": "vae"
|
| 1216 |
}
|
| 1217 |
]
|
workflows/{p-h3-image_text_to_image.json → p-image-oss_text_to_image.json}
RENAMED
|
@@ -348,10 +348,10 @@
|
|
| 348 |
"ver": "0.43.0"
|
| 349 |
},
|
| 350 |
"widgets_values": [
|
| 351 |
-
"p-
|
| 352 |
],
|
| 353 |
"widgets_values_named": {
|
| 354 |
-
"filename_prefix": "p-
|
| 355 |
}
|
| 356 |
},
|
| 357 |
{
|
|
@@ -408,7 +408,7 @@
|
|
| 408 |
]
|
| 409 |
}
|
| 410 |
],
|
| 411 |
-
"title": "p-
|
| 412 |
"properties": {
|
| 413 |
"Node name for S&R": "CLIPLoader",
|
| 414 |
"cnr_id": "comfy-core",
|
|
@@ -416,7 +416,7 @@
|
|
| 416 |
"models": [
|
| 417 |
{
|
| 418 |
"name": "p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 419 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 420 |
"directory": "text_encoders"
|
| 421 |
}
|
| 422 |
]
|
|
@@ -944,7 +944,7 @@
|
|
| 944 |
"models": [
|
| 945 |
{
|
| 946 |
"name": "p-h3-image_bf16.safetensors",
|
| 947 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 948 |
"directory": "diffusion_models"
|
| 949 |
}
|
| 950 |
]
|
|
@@ -1074,13 +1074,13 @@
|
|
| 1074 |
]
|
| 1075 |
}
|
| 1076 |
],
|
| 1077 |
-
"title": "p-
|
| 1078 |
"properties": {
|
| 1079 |
"Node name for S&R": "CLIPLoader",
|
| 1080 |
"models": [
|
| 1081 |
{
|
| 1082 |
"name": "p-h3-image_text_encoder_bf16.safetensors",
|
| 1083 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 1084 |
"directory": "text_encoders"
|
| 1085 |
}
|
| 1086 |
]
|
|
@@ -1136,7 +1136,7 @@
|
|
| 1136 |
"models": [
|
| 1137 |
{
|
| 1138 |
"name": "p-h3-image_vae_bf16.safetensors",
|
| 1139 |
-
"url": "https://huggingface.co/PrunaAI/P-
|
| 1140 |
"directory": "vae"
|
| 1141 |
}
|
| 1142 |
]
|
|
|
|
| 348 |
"ver": "0.43.0"
|
| 349 |
},
|
| 350 |
"widgets_values": [
|
| 351 |
+
"p-image-oss"
|
| 352 |
],
|
| 353 |
"widgets_values_named": {
|
| 354 |
+
"filename_prefix": "p-image-oss"
|
| 355 |
}
|
| 356 |
},
|
| 357 |
{
|
|
|
|
| 408 |
]
|
| 409 |
}
|
| 410 |
],
|
| 411 |
+
"title": "p-image-oss prompt upsampler",
|
| 412 |
"properties": {
|
| 413 |
"Node name for S&R": "CLIPLoader",
|
| 414 |
"cnr_id": "comfy-core",
|
|
|
|
| 416 |
"models": [
|
| 417 |
{
|
| 418 |
"name": "p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 419 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/text_encoders/p-h3-image_prompt_upsampler_bf16.safetensors",
|
| 420 |
"directory": "text_encoders"
|
| 421 |
}
|
| 422 |
]
|
|
|
|
| 944 |
"models": [
|
| 945 |
{
|
| 946 |
"name": "p-h3-image_bf16.safetensors",
|
| 947 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/diffusion_models/p-h3-image_bf16.safetensors",
|
| 948 |
"directory": "diffusion_models"
|
| 949 |
}
|
| 950 |
]
|
|
|
|
| 1074 |
]
|
| 1075 |
}
|
| 1076 |
],
|
| 1077 |
+
"title": "p-image-oss text encoder",
|
| 1078 |
"properties": {
|
| 1079 |
"Node name for S&R": "CLIPLoader",
|
| 1080 |
"models": [
|
| 1081 |
{
|
| 1082 |
"name": "p-h3-image_text_encoder_bf16.safetensors",
|
| 1083 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/text_encoders/p-h3-image_text_encoder_bf16.safetensors",
|
| 1084 |
"directory": "text_encoders"
|
| 1085 |
}
|
| 1086 |
]
|
|
|
|
| 1136 |
"models": [
|
| 1137 |
{
|
| 1138 |
"name": "p-h3-image_vae_bf16.safetensors",
|
| 1139 |
+
"url": "https://huggingface.co/PrunaAI/P-Image-OSS-Comfy/resolve/main/vae/p-h3-image_vae_bf16.safetensors",
|
| 1140 |
"directory": "vae"
|
| 1141 |
}
|
| 1142 |
]
|