How to run FLUX.1 Kontext in ComfyUI on a cloud GPU

Rent a GPU on Deploy, then open the ComfyUI template. Follow the official ComfyUI FLUX examples page for FLUX.1 Kontext [dev]: put the diffusion file it links in ComfyUI/models/diffusion_models/, add the text encoders and VAE that page names, drag its example image into ComfyUI, and copy the output folder off the instance before you destroy it. Destroying the instance deletes its disk.

The model card says this model falls under the FLUX.1 [dev] Non-Commercial License (read 2026-11-12). The file model_licenses/LICENSE-FLUX1-dev in the upstream flux repository is titled FLUX.1 [dev] Non-Commercial License v1.1.1, and its definition of the FLUX.1 [dev] Model includes FLUX.1 Kontext [dev]. Section 2 grants use of the weights only for Non-Commercial Purposes as that file defines them. Section 2(d) says the license claims no ownership of outputs, that you may use an output for any purpose, including a commercial purpose, except as the license prohibits, and that you may not use an output to train, fine-tune, or distill a model that is competitive with the FLUX.1 [dev] Model or the FLUX.1 Kontext [dev] Model. Section 2(e) requires content filters or a review for unlawful or infringing content, and a disclosure that the output was generated or modified with artificial intelligence where the law requires it. Section 4 prohibits uses that include surveillance, biometric processing, unlawful content, child sexual abuse material, and non-consensual intimate images. A commercial or production use of the weights is not granted by this text. Read the file. This page does not restate the rest of it. The LICENSE.md inside the gated model repository returned HTTP 401 on 2026-11-12, so this page does not claim that file is the same text.

The commands below are copied from the upstream pages named in each step. They were not run on a CloudGPU instance for this page. Anything this page adds around them is marked.

What the model card and the examples page say about memory

The model card linked from the ComfyUI examples page says FLUX.1 Kontext [dev] is a 12 billion parameter rectified flow transformer that edits images from text instructions (read 2026-11-12). This page does not copy that Hub id. That parameter count is not a VRAM figure. The card text publishes no GPU GB figure. It says the model is available in ComfyUI and in Diffusers, and its Diffusers example sets guidance_scale=2.5. This page follows the ComfyUI examples route and does not paste that Diffusers snippet. The snippet’s from_pretrained argument is a Hub id this page does not copy.

The ComfyUI FLUX examples page publishes no GPU GB figure for Kontext (read 2026-11-12). It says the fp16 text encoder is recommended if you have more than 32GB ram. That sentence is system RAM, not a catalog vram_gb. The same page says you can set weight_dtype to fp8 on the Load Diffusion Model node, which “will lower the memory usage by half”, and that an fp8 file exists “if the other one is too large for you.” Neither sentence is a GB cutoff.

GET /v1/public/compute-capabilities does not list GPUs. It returns feature flags. The memory column is vram_gb from gpu-prices.json, updated_at 2026-11-12T16:09:18.550Z. GET /v1/public/gpu-catalog the same day (generated_at 2026-11-12T16:09:17.753Z) listed the same names and the same vram_gb values, plus Ascend 910B, which is not in gpu-prices.json and is not listed here. The catalog response also includes an availability field. This page does not copy it. There is no upstream GPU GB cutoff to match these values against. Which listing you can start is on Deploy. This page does not say which listings are available.

Catalog name vram_gb
RTX 2080 8
RTX 3080 10
RTX 2080 Ti 11
RTX 3080 Ti 12
V100 16G 16
A30 24
RTX 3090 24
RTX 4090 24
RTX 4090D 24
RTX 4080 SUPER 32G 32
RTX 5090 32
RTX 5090D 32
V100 32G 32
A100 40G 40
A800 40G 40
A40 48
RTX 4090 48G 48
RTX 4090D 48G 48
RTX A6000 48
NVIDIA RTX PRO 5000 72G 72
RTX PRO 5000 72G 72
A100 80G 80
A800 80G 80
H800 80
RTX 6000D 83
H20 96G 96
RTX PRO 6000 96G 96
RTX PRO 6000 Max-Q 96

The catalog template whose name is ComfyUI has id flux-1-dev, recommended_gpu RTX 4090 48G, and min_vram_gb 24 (read 2026-11-12). Those three fields are the template record. They are not a Kontext figure from the model card or the examples page.

Install on the ComfyUI template

On Deploy, choose the template named ComfyUI. How to choose a rental GPU for ComfyUI is the card page for that template. How to run FLUX.1-dev in ComfyUI uses the same template for a different checkpoint, and how to run Qwen-Image is the other image guide. The FLUX.1-dev guide says the template installs ComfyUI only and does not include FLUX weights, citing CloudGPU’s docs as read on 2026-11-03. This page did not re-read those docs. Read the template description on Deploy before you rely on that sentence.

The examples page does not print a shell command that finds the ComfyUI directory. This page adds the same lookup the FLUX.1-dev guide uses. It was not run for this page.

COMFY=$(find / -maxdepth 4 -type d -name ComfyUI 2>/dev/null | head -n 1); echo "$COMFY"

Files the examples page names

The Kontext section says the examples might require the regular flux files linked at the top of that page. Those placement lines, copied:

Text encoders go in ComfyUI/models/text_encoders/. The page links t5xxl_fp16.safetensors and clip_l.safetensors, and says you can use t5xxl_fp8_e4m3fn_scaled.safetensors instead for lower memory usage, with the fp16 file recommended if you have more than 32GB ram. That link is https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main.

The VAE goes in ComfyUI/models/vae/. The page links https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/blob/main/split_files/vae/ae.safetensors.

The Kontext diffusion file, copied from that section: download flux1-kontext-dev.safetensors and put it in ComfyUI/models/diffusion_models/. The page links that file. This page does not copy the Hub id on the link. The model API for that repository, read 2026-11-12, reported gated: auto and pipeline_tag: image-to-image. The file listing reported flux1-kontext-dev.safetensors at 23802947360 bytes and ae.safetensors at 335304388 bytes. Those are file sizes, not VRAM. The examples page tells you to take the VAE from the Comfy-Org link above. This page does not assume the two ae.safetensors files are the same bytes. Because the repository is gated, accept the license on the model page with your Hugging Face account before the download. How to download a Hugging Face model is the hf download reference. The examples page does not print an hf download command. cloudgpu-net is not on that page. The download speed guide says to leave it off during pip, then turn it on for a weight download.

The alternative file, copied: flux1-dev-kontext_fp8_scaled.safetensors, “if the other one is too large for you.” The examples page links https://huggingface.co/Comfy-Org/flux1-kontext-dev_ComfyUI/blob/main/split_files/diffusion_models/flux1-dev-kontext_fp8_scaled.safetensors. A model API request for Comfy-Org/flux1-kontext-dev_ComfyUI on 2026-11-12 returned id Comfy-Org/Flux-1-Kontext-Dev, gated: false, and pipeline_tag: text-to-image. The file listing reported that safetensors file at 11904640136 bytes. That is a file size, not VRAM. The license section above still covers FLUX.1 Kontext [dev] weights. This page did not compare the fp8 bytes with the full file.

Workflow

The examples page says you can load or drag its Kontext example image into ComfyUI to get the workflow. It also links an input image and a second example that generates a comic from that input. This page does not restate node values that are only inside those images. The model card’s guidance_scale=2.5 is the Diffusers example, not a value this page read out of the ComfyUI image.

Refresh ComfyUI so it sees the new files. To open the page, use the public HTTPS URL the ComfyUI template shows on the instance row, or an SSH tunnel. The FLUX.1-dev guide uses a tunnel to port 8188 for this template. This page did not re-check that port. How to use SSH port forwarding is the forwarding reference.

When it fails

CUDA out of memory. The model card and the examples page publish no GPU GB cutoff. The examples page says to use the fp8 file if the other one is too large, or to set weight_dtype to fp8 on Load Diffusion Model. Then use how to fix CUDA out of memory on a cloud GPU.

“CUDA error: no kernel image is available” on an RTX 5090. Catalog RTX 5090 and RTX 5090D are 32 GB. That is the catalog value, not a Kontext requirement. The examples page does not pin a PyTorch build. The RTX 5090 guide says that card needs a PyTorch build for CUDA 12.8 or newer. This page did not re-test the ComfyUI template on an RTX 5090.

Gated download. The model API reported gated: auto for the repository that hosts flux1-kontext-dev.safetensors. Accept the license on that model page, then download again. The Comfy-Org file above reported gated: false. The license in the first section still applies to FLUX.1 Kontext [dev].

Save the images, then destroy

ComfyUI writes images under the output directory inside the ComfyUI folder. Copy that directory, and any workflow you exported, before you destroy the instance. Save your work before you destroy a cloud GPU is the checklist. The terms say data on local instance storage is permanently deleted when the instance is destroyed. Billing is per minute, with a 1-minute minimum, and it stops when you destroy the instance. The billing rule is on the pricing page. Prices are not copied here.

Frequently asked questions

How much VRAM does FLUX.1 Kontext [dev] publish?

The FLUX.1 Kontext [dev] model card and the official ComfyUI FLUX examples page publish no GPU GB figure (read 2026-11-12). The card says the model is a 12 billion parameter rectified flow transformer. That is a parameter count, not a VRAM figure. The examples page says the fp16 text encoder is recommended if you have more than 32GB ram. That sentence is system RAM, not a catalog vram_gb. This page does not mark any catalog vram_gb as enough or not enough. Which listing you can start is on https://cloudgpu.app/deploy.

What license covers FLUX.1 Kontext [dev]?

The model card says the model falls under the FLUX.1 [dev] Non-Commercial License. model_licenses/LICENSE-FLUX1-dev in the upstream flux repository is version 1.1.1 and includes FLUX.1 Kontext [dev] in the model definition (read 2026-11-12). Section 2 limits use of the weights to Non-Commercial Purposes as that file defines them. Section 2(d) says outputs may be used for any purpose, including commercial purposes, except as the license prohibits, and that outputs may not be used to train, fine-tune, or distill a competitive model. Section 2(e) requires content filters or review, and an AI disclosure where the law requires one. Read that file before you use the weights. This page did not compare it with the LICENSE.md inside the gated model repository.

Where does the official ComfyUI example put the Kontext weights?

The ComfyUI FLUX examples page says to download flux1-kontext-dev.safetensors and put it in ComfyUI/models/diffusion_models/. It links flux1-dev-kontext_fp8_scaled.safetensors if the other file is too large. The same page says the Kontext examples might require the regular flux text encoders and VAE named at the top of that page. Drag the example image on that page into ComfyUI to load the workflow. This page does not copy the Hub id on the full-weight link.

Do the images stay on the instance after I destroy it?

No. Copy the ComfyUI output folder off the instance before you destroy it. The terms say data on local instance storage is permanently deleted when the instance is destroyed.

Sources (read 2026-11-12, Asia/Shanghai)

Cards you can start are on the Deploy page. Prices are on https://cloudgpu.app/pricing and are not repeated here.

Last updated: 2026-11-12 (Asia/Shanghai).