wehub/nvidia--tensorrt
1
0
Fork 0
Code Issues Pull Requests Actions 15 Deployments Models Agent Notes Packages Projects Releases Wiki Activity
Files
main
nvidia--tensorrt/demo/Diffusion/docs/support_matrix.md
T
wehub-resource-sync c8a779b1bb
Docker Image CI / build-ubuntu2004 (push) Waiting to run
Details
chore: import upstream snapshot with attribution
2026-07-13 13:36:55 +08:00

34 lines
14 KiB
Markdown
Raw Permalink Blame History

<!--- SPDX-License-Identifier: Apache-2.0 -->
# Supported Diffusion Models
This demo supports Diffusion models that are popular in the Generative AI community. The table below lists the various configurations we support for each pipeline.
## Pipeline Support Matrix
| Pipeline | Version | Task | Supported Precisions | Additional features | Hub | Restrictions |
|------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------|-----------------------------------------------|--------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Stable Diffusion | 1.4 | <ul><li>Text-to-image</li><li>Image-to-image</li></ul> | FP16, FP8, INT8 * | N/A | [CompVis/stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4) | |
| Stable Diffusion | dreamshaper-7 | <ul><li>Text-to-image</li><li>Image-to-image</li></ul> | FP16 | N/A | [Lykon/dreamshaper-7](https://huggingface.co/Lykon/dreamshaper-7) |
| Stable Diffusion | [XL 1.0-base](../README.md#generate-an-image-with-stable-diffusion-xl-guided-by-a-single-text-prompt) | <ul><li>Text-to-image</li><li>Image-to-image</li></ul> | FP16, FP8, INT8 * | LoRA (FP16, BF16, FP8) | [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) |
| Stable Diffusion | [XL 1.0-refiner](../README.md#generate-an-image-with-stable-diffusion-xl-guided-by-a-single-text-prompt) | <ul><li>Text-to-image</li><li>Image-to-image</li></ul> | FP16 | N/A | [stabilityai/stable-diffusion-xl-refiner-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0) |
| Stable Diffusion | [XL-Turbo](../README.md#faster-text-to-image-using-sdxl-turbo) | <ul><li>Text-to-image</li><li>Image-to-image</li></ul> | FP16 | N/A | [stabilityai/sdxl-turbo](https://huggingface.co/stabilityai/sdxl-turbo) |
| Stable Diffusion | [3](../README.md#generate-an-image-guided-by-a-text-prompt-using-stable-diffusion-3) | <ul><li>Text-to-image</li></ul> | FP16 | N/A | [stabilityai/stable-diffusion-3-medium](https://huggingface.co/stabilityai/stable-diffusion-3-medium) |
| Stable Diffusion | [3.5-medium](../README.md#generate-an-image-guided-by-a-text-prompt-using-stable-diffusion-3) | <ul><li>Text-to-image</li></ul> | FP16, BF16 | N/A | [stabilityai/stable-diffusion-3-medium](https://huggingface.co/stabilityai/stable-diffusion-3-medium) |
| Stable Diffusion | [3.5-large](../README.md#generate-an-image-guided-by-a-text-prompt-using-stable-diffusion-3) | <ul><li>Text-to-image</li></ul> | FP16, BF16, FP8 | N/A | [stabilityai/stable-diffusion-3-large](https://huggingface.co/stabilityai/stable-diffusion-3-large) |
| ControlNet | [1.4](../README.md#generate-an-image-with-controlnet-guided-by-images-and-text-prompts) | <ul><li>Image-to-image</li></ul> | FP16 | N/A | <ul><li>[lllyasviel/sd-controlnet-canny](https://huggingface.co/lllyasviel/sd-controlnet-canny)</li><li>[lllyasviel/sd-controlnet-depth](https://huggingface.co/lllyasviel/sd-controlnet-depth)</li><li>[lllyasviel/sd-controlnet-hed](https://huggingface.co/lllyasviel/sd-controlnet-hed)</li><li>[lllyasviel/sd-controlnet-mlsd](https://huggingface.co/lllyasviel/sd-controlnet-mlsd)</li><li>[lllyasviel/sd-controlnet-normal](https://huggingface.co/lllyasviel/sd-controlnet-normal)</li><li>[lllyasviel/sd-controlnet_openpose](https://huggingface.co/lllyasviel/sd-controlnet-openpose)</li><li>[lllyasviel/sd-controlnet_scribble](https://huggingface.co/lllyasviel/sd-controlnet-scribble)</li><li>[lllyasviel/sd-controlnet_seg](https://huggingface.co/lllyasviel/sd-controlnet-seg)</li></ul> |
| ControlNet | [XL 1.0-base](../README.md#generate-an-image-with-stable-diffusion-xl-guided-by-a-single-text-prompt) | <ul><li>Image-to-image</li></ul> | FP16, FP8 | N/A | [stabilityai/controlnet-canny-sdxl-1.0](https://huggingface.co/diffusers/controlnet-canny-sdxl-1.0) |
| ControlNet | [3.5-large](../README.md#generate-an-image-with-stable-diffusion-v35-large-with-controlnet-guided-by-an-image-and-a-text-prompt) | <ul><li>Image-to-image</li></ul> | FP16, BF16, FP8 (canny and depth only) | N/A | <ul><li>[stabilityai/stable-diffusion-3.5-large-controlnet-canny](https://huggingface.co/stabilityai/stable-diffusion-3.5-large-controlnet-canny)</li><li>[stabilityai/stable-diffusion-3.5-large-controlnet-depth](https://huggingface.co/stabilityai/stable-diffusion-3.5-large-controlnet-depth)</li><li>[stabilityai/stable-diffusion-3.5-large-controlnet-blur](https://huggingface.co/stabilityai/stable-diffusion-3.5-large-controlnet-blur)</li></ul> |
| Stable Video Diffusion | [XT-1.1](../README.md#generate-a-video-guided-by-an-initial-image-using-stable-video-diffusion) | <ul><li>Text-to-video</li></ul> | FP16, FP8 | N/A | [stabilityai/stable-video-diffusion-img2vid-xt-1-1](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1) |
| Stable Cascade | [N/A](../README.md#generate-an-image-guided-by-a-text-prompt-using-stable-cascade) | <ul><li>Text-to-image</li></ul> | BF16 | N/A | <ul><li>[stabilityai/stable-cascade-prior](https://huggingface.co/stabilityai/stable-cascade-prior)</li><li>[stabilityai/stable-cascade](https://huggingface.co/stabilityai/stable-cascade)</li></ul> |
| Flux | [1-Dev](../README.md#generate-an-image-guided-by-a-text-prompt-using-flux) | <ul><li>Text-to-image</li><li>Image-to-image</li></ul> | FP16, BF16, FP8, FP4 * | LoRA (FP16, BF16, FP8) | [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) |
| Flux | [1-Schnell](../README.md#generate-an-image-guided-by-a-text-prompt-using-flux) | <ul><li>Text-to-image</li><li>Image-to-image</li></ul> | FP16, BF16, FP8, FP4 * | LoRA (FP16, BF16, FP8) | [black-forest-labs/FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) |
| Flux | [1-Canny-Dev](../README.md#generate-an-image-guided-by-a-text-prompt-and-a-control-image-using-flux-controlnet) | <ul><li>Image-to-image</li></ul> | FP16, BF16, FP8, FP4 | N/A | [black-forest-labs/FLUX.1-Canny-dev](https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev) |
| Flux | [1-Depth-Dev](../README.md#generate-an-image-guided-by-a-text-prompt-and-a-control-image-using-flux-controlnet) | <ul><li>Image-to-image</li></ul> | FP16, BF16, FP8, FP4 | N/A | [black-forest-labs/FLUX.1-Depth-dev](https://huggingface.co/black-forest-labs/FLUX.1-Depth-dev) |
| Flux | [1-Kontext-Dev](../README.md#5-edit-an-image-using-flux-kontext) | <ul><li>Image-to-image</li></ul> | BF16, FP8, FP4 | N/A | [black-forest-labs/FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) |
| Cosmos | [cosmos-predict2-2b-text2image](../README.md#1-generate-an-image-from-a-text-prompt-1), cosmos-predict2-14b-text2image | <ul><li>Text-to-image</li></ul> | BF16 | N/A | <ul><li>[nvidia/Cosmos-Predict2-2B-Text2Image](https://huggingface.co/nvidia/Cosmos-Predict2-2B-Text2Image)</li><li>[nvidia/Cosmos-Predict2-14B-Text2Image](https://huggingface.co/nvidia/Cosmos-Predict2-14B-Text2Image) |
| Cosmos | [cosmos-predict2-2b-video2world](../README.md#2-generate-a-video-guided-by-an-initial-video-conditioning-and-a-text-prompt), cosmos-predict2-14b-video2world | <ul><li>Video-to-World</li></ul> | BF16 | N/A | <ul><li>[nvidia/Cosmos-Predict2-2B-Video2World](https://huggingface.co/nvidia/Cosmos-Predict2-2B-Video2World)</li><li>[nvidia/Cosmos-Predict2-14B-Video2World](https://huggingface.co/nvidia/Cosmos-Predict2-14B-Video2World) |
| Wan | [2.2-T2V-A14B](../README.md#generate-a-video-from-a-text-prompt-using-wan) | <ul><li>Text-to-video</li></ul> | BF16 | N/A | [wan-ai/wan2.2-t2v-a14b](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers) |
*Note: Only the text2image pipelines support FP4/FP8/INT8 quantization. The image2image pipelines don't support quantization.
Reference in New Issue View Git Blame Copy Permalink